outlook-mcp

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v3.9.1
Disambiguation5/5
Each tool targets a distinct aspect of Outlook (auth, mail, calendar, contacts, settings, etc.) with clear boundaries. Even similar operations like 'search-emails' and 'read-email' or 'send-email' and 'draft' have well-defined differences in purpose and usage.
Naming Consistency4/5
Most tool names follow a consistent verb_noun pattern (e.g., search-emails, send-email). A few outliers like 'auth', 'attachments', and 'draft' break the pattern but are still intuitive and recognizable.
Tool Count5/5
With 22 tools, the server covers a broad yet focused set of Outlook capabilities without being overwhelming. Each tool serves a clear purpose, and the count aligns well with the server's scope.
Completeness4/5
The tool set covers major Outlook workflows (mail, calendar, contacts, settings, rules) but has minor gaps like lacking a calendar list tool beyond the default calendar and no support for contact groups or distribution lists.
Average 4.7/5 across 22 of 22 tools scored.
See the Tool Scores section below for per-tool breakdowns.
- 0 of 2 community issues answered or closed in the last 6 months
- 23 commits in the last 12 weeks
- Last stable release on August 1, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
This repository includes a glama.json configuration file.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description contradicts the annotations. It explicitly includes action=delete which removes an override, yet annotations declare destructiveHint=false. This is a serious inconsistency that could mislead an agent about the tool's safety profile. Despite otherwise helpful behavioral details (e.g., list output, set creates or updates), the contradiction forces a low score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense paragraph that front-loads the purpose, then cleanly explains each action and its parameters. The critical caveat is included without unnecessary fluff. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description covers the list return format and the account prerequisite. It misses explicit return values for set/delete, but overall it provides a clear behavioral model for the tool. This is nearly complete for a management tool with five parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining the list return format (id/sender/classifyAs), clarifies that set creates or updates, and notes the effect on future mail routing. These additions help the agent understand parameter usage in context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages Focused Inbox sender overrides, explaining the exact mechanism (forcing messages into Focused or Other regardless of the ML classifier). It also enumerates specific actions (list/set/delete), distinguishing it from sibling tools like manage-rules or manage-category.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides strong usage context, including when each action should be used and a critical caveat that it only works on accounts with Focused Inbox enabled. It does not explicitly name alternative tools, but the domain is clearly scoped enough to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behavioral details such as default attachment inclusion, format dependencies, and disk-writing intent (savePath, outputDir). While annotations already indicate readOnlyHint=false and destructiveHint=false, the description adds context on side effects and size limits. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose and organized by target, but it is somewhat lengthy. However, every sentence adds necessary detail for a 14-parameter tool with four modes. It is appropriately structured and not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of an output schema, the description covers all four targets, format compatibilities, defaults, and parameter usage. It lacks explicit mention of what the tool returns (e.g., file path or bytes), but it contextually implies file operations. Generally complete for the task.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the baseline is high. The description adds significant value by explaining parameter interactions (e.g., target-specific format enums, query shortcut, includeAttachments defaults), going well beyond the schema's individual descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Export emails to file formats for archival, forensics, or programmatic processing,' specifying the verb and resource. It distinguishes from sibling tools like read-email and attachments by focusing on file export rather than viewing or handling attachments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides detailed guidance on when to use each target (message, messages, conversation, mime) and explains defaults and alternatives (e.g., emailIds vs searchQuery). However, it does not explicitly contrast with sibling tools or state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds behavioral details beyond annotations: returns specific fields, default timezone, UTC authoritative datetime format. Annotations already indicate read-only, but description clarifies scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose, each sentence adds value. Slightly long but necessary to cover return format and timezone behavior. Well-organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lists return fields and datetime format, but missing pagination details beyond page size (e.g., how to get next page). No output schema, so description covers most needed context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (count) with 100% schema coverage. Description repeats schema info (default, max) but does not add new semantic context beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Explicitly states it lists upcoming calendar events for the signed-in user and is read-only. Clearly distinguishes from siblings like create-event and read-email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says this tool does not filter and directs to alternatives (Outlook UI or Graph API) for filtered queries. Also explains count parameter for page size control.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool is destructive (covers delete) and that 'permanentDelete' is intentionally omitted for safety. It explains that rules run server-side regardless of client, supports dryRun for preview, and is subject to session rate limits. This adds significant value beyond the annotations (destructiveHint=true).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense paragraph covering many aspects. It is front-loaded with the main purpose but could benefit from bullet points or clearer separation of actions. However, given the tool's complexity with 37 parameters, it remains reasonably efficient without redundant sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 37 parameters, no output schema, and only basic annotations, the description covers all necessary context: all actions are explained, parameters are grouped logically, safe preview via dryRun is highlighted, dangerous operations are excluded, and rate limits are noted. It is fully adequate for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the input schema already describes each parameter (100% coverage), the description groups condition parameters (12 supported), action parameters (9 supported), and exception parameters, and explains the logical OR for keyword searches. It clarifies the relationship between 'name' and 'displayName' and provides examples (e.g., 'invoice, receipt'). This adds meaningful semantic grouping.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Server-side inbox rule CRUD' and enumerates each action (list, create, update, reorder, delete), specifying that it covers destructive operations. It distinguishes itself from sibling tools like 'manage-focused-inbox' and 'apply-category' by focusing on inbox rules, and mentions intentional omission of permanentDelete as too dangerous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit context for each action: default action is list, dryRun for preview, reorder changes sequence, etc. It also warns about rate limits and the omission of permanentDelete. However, it does not explicitly compare to sibling tools or advise when to use this tool over others like 'manage-focused-inbox'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses return format (Markdown vs JSON), conditional headers (forensic vs basic), and output verbosity. Annotations already indicate read-only and open world; the description adds behavioral details on stripping HTML, attachment metadata, and mode combinations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single dense paragraph is well-structured: core action first, then defaults, then conditional modes. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters and no output schema, description sufficiently covers all modes, default returns, and formatting options. No gaps for typical usage scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 7 parameters (100% coverage). Description enriches semantics by explaining parameter interactions (e.g., headersMode with importantOnly, groupByType, raw) and default values for outputVerbosity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Read a single email by id (read-only)' with specific verb and resource. Default output and conditional modes are detailed, distinguishing it from sibling tools like send-email or draft.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description explains default behavior and various modes (headersMode, includeHeaders, outputVerbosity), providing clear context for different use cases. However, no explicit when-to-use or when-not-to-use compared to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses that list is read-only, view retrieves content, and download saves to disk. It also notes auto-creation of outputDir and behavior for binary types. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficient (~100 words), front-loads the core purpose, and uses clear structure (action=...). Every sentence conveys essential information without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers all three actions, parameter requirements, and edge cases (binary types, directory creation). However, it does not specify the exact return format for the list action, though it lists metadata fields. Missing output schema is partly offset.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by specifying defaults (system tmpdir for outputDir), auto-creation, deprecation of savePath, and requirement of attachmentId for view/download, going beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Inspect or retrieve email attachments' and enumerates three distinct actions (list, view, download) with specific purposes. It differentiates from sibling tools like read-email by focusing solely on attachments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use each action (e.g., 'view returns inline content for text/JSON/XML attachments; binary types require download'). However, it does not explicitly state when not to use this tool or mention alternatives among sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses important behavioral nuances: automatic fallback through OData filters / boolean filters / recent listing on Outlook.com, deprecated alias behavior for kqlQuery, auto-quoting of search tokens, and the mechanics of delta tokens for incremental sync. This adds significant value beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-organized, front-loading the core purpose and then systematically explaining each mode. It is long, but given 21 parameters and multiple modes, every sentence contributes necessary information without fluff. A tighter structure with bullet points could improve readability, but no sentence is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers return values ("Returns paged messages with id/subject/from/receivedDateTime/preview by default"), mode behavior, personal account limitations, and parameter interactions. With no output schema, this is sufficient context for an agent to select and invoke the tool correctly across all its modes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the input schema already covers all 21 parameters with descriptions, the tool description explains how parameters interact to select modes (e.g., deltaMode with deltaToken, searchExpression bypassing other params, groupByConversation vs conversationId). This cross-parameter semantic guidance goes beyond what the schema provides, though the baseline is 3 due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb+resource statement: "Search, list, delta-sync, or thread-group emails — six modes selected by parameters (read-only)." It enumerates the distinct modes and explicitly notes the tool is read-only, which distinguishes it from sibling mutation tools like send-email and update-email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides detailed guidance on when to use each mode, such as "ideal for inbox monitoring" for delta mode and explicit fallback behavior on personal Outlook.com accounts. It does not explicitly contrast with direct alternatives like read-email for single-message lookup, but the mode distinctions and parameter guidance adequately convey usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description's mention of 'read-only' is consistent but not additional. The description adds behavioral context: paged returns, same shape as search-emails, defaults for folder and count, and outputVerbosity for detail control. This is sufficient, though rate limits or error conditions are not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at about 4 lines, with no redundant sentences. It is front-loaded with the core purpose and then provides necessary details in a logical order. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description explains the return shape (id/subject/from/receivedDateTime/preview) and references the sibling tool's list mode. It covers prerequisites, parameter defaults, and alternatives. For a list tool with this complexity, the description is fully adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds meaning by explaining the purpose of 'email' as an alias for 'sharedMailbox', default values for 'folder' and 'count', and the role of 'outputVerbosity' with its enum options. This extra context justifies a score above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action ('List emails'), resource ('shared mailbox'), and read-only nature. It distinguishes itself from sibling tools by referencing 'search-emails' as an alternative for full search/filter capability.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool (list emails from a delegated shared mailbox) and when to use an alternative ('prefer search-emails with a folder path scoped to the shared mailbox' for full search/filter). It also mentions the prerequisite that the mailbox must be admin-configured and delegated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by detailing exact mutation semantics: `set` replaces, `add` appends, `remove` removes only named categories. It also discloses the matching-by-display-name behavior, the Graph `$batch` mechanism, and the per-message confirmation return, all of which are non-obvious and useful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences long, each earning its place. It starts with the core purpose, then explains actions, parameter options, prerequisites, and return value in a logical flow. No redundant filler or restatement of the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with four parameters, no output schema, and moderate complexity, the description covers all necessary aspects: purpose, action semantics, prerequisite (categories must exist), single/batch variants, and return value. It also correctly references the sibling `manage-category` tool, making the description complete in context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the input schema already covers all parameters (100% coverage), the description adds critical meaning: it explains that `messageId` and `messageIds` are alternatives (not combinable), that `categories` are matched by display name, and that `action` defaults to `set`. This extra context enriches the parameter understanding beyond the schema's terse descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb+resource statement: 'Tag or untag email messages with master categories.' It specifies the three actions (set, add, remove) and distinguishes itself from sibling tool `manage-category` (which creates categories). The purpose is unambiguous and specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context by referencing `manage-category` as the prerequisite for creating categories and explicitly notes that category names must already exist in the master list. It also explains single vs. batch usage. It doesn't explicitly list alternative tools for 'when not to use this', but the workflow context is strong enough to guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint: true, and the description elaborates on behaviors such as permanent deletion, rate limit sharing for send, and mutual exclusivity of comment and body. This adds significant context beyond the annotations, with no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with a summary and then enumerates actions clearly. While every sentence adds value, it could be more structured (e.g., bulleted actions) to improve readability. Overall, it is efficient but slightly dense.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 11 parameters and 7 actions, the description covers all actions, their parameter requirements, return values, and special behaviors (e.g., dryRun, checkRecipients). The lack of output schema is compensated by explicit return descriptions. No critical gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameters have 100% schema description coverage, but the tool description adds critical context not in the schema, such as 'Cannot combine with body' for comment, 'runs mail-tips first' for checkRecipients, and 'preview without saving' for dryRun. This provides essential usage details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it covers the full draft lifecycle with seven specific actions (create, update, send, delete, reply, reply-all, forward). Each action is explicitly described with its purpose and required inputs, distinguishing it from sibling tools like send-email and read-email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides guidance on when to use each action, including dryRun and checkRecipients for create, and notes that send shares rate limit with send-email. However, it does not explicitly state when to use an alternative tool instead (e.g., using send-email directly), leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description richly discloses behavioral details beyond the annotations: destructive delete semantics, read-only sub-actions, name/path/ID resolution, ambiguous-name fallback, and provider-specific differences (Outlook.com vs M365/Exchange). It clarifies and extends the destructiveHint annotation without contradicting it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense paragraph that packs in a lot of necessary information. It's not a model of conciseness, but every sentence adds operational value given the tool's complexity. A bulleted structure might improve scannability, but the length is justified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 14-parameter tool with no output schema, the description is remarkably complete. It covers all actions, addressing schemes, return values (e.g., list output includes path and [id: ...]), constraints (cannot delete protected folders), and provider behavior differences. It leaves no major operational gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the schema already covers all parameters, the description adds crucial semantics: how name/path/ID addressing works, case-insensitivity, path examples, and which parameters pair with which actions (e.g., parentFolder vs parentFolderId). This is far more valuable than the schema's isolated field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as managing mail folders and enumerates five specific actions (list, create, move, stats, delete), each with a distinct purpose. It differentiates from sibling email tools by focusing entirely on folder operations and provides concrete examples of addressing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Each action has explicit context: when to use it, required parameters, and defaults (e.g., 'action=list (default) returns the folder tree'). The description notes stats is 'suitable for pagination planning' and explains move/delete prerequisites. It doesn't explicitly name alternatives among sibling tools, but the scope is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Thoroughly discloses destructive behavior (cancel notifies attendees, delete permanently removes), PATCH semantics (only fields passed are changed), and dryRun side-effect-free preview. This adds significant value beyond the destructiveHint annotation and covers return behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Despite being long, the description is well-organized by action, front-loaded with the destructive warning, and every sentence serves a purpose given the complex multi-action tool. No redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Comprehensive: covers all actions, dryRun, accept limitation, return values, and PATCH merge behavior. With 17 params and no output schema, the description plus schema fully specify the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds critical semantics like 'only fields you pass are changed', 'full replacement list' for attendees/categories, and action-specific applicability. This enriches the schema-provided definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it manages existing calendar events (update/decline/cancel/delete) and differentiates from siblings like create-event and list-events. The four action types are enumerated, making the purpose specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance on when to use each action, including dryRun for previewing PATCH, and explicitly notes there is no accept action and instructs to use the Outlook UI instead. It lacks an explicit contrast with list-events/create-event but the scoping is evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and openWorldHint=true. The description adds that the tool uses Microsoft Graph People API, is read-only, and returns specific fields. No contradictions. It adds value beyond annotations but does not mention rate limits or pagination behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. First sentence states core function, second sentence provides use cases and differentiation. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with no output schema, the description covers return fields, purpose, and differentiation. Annotations cover read-only and open-world aspects. Contextually complete given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described. The description adds context that query can be 'name, email, company' and that count max is 50 (schema says max: 50). This enhances understanding beyond the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Relevance-ranked search across personal contacts, organisation directory, and recent communications via the Microsoft Graph People API (read-only)' with specific return fields. It distinguishes from sibling tool 'manage-contact' with action='search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states ideal use cases ('who is X?', 'who do I email about Y?') and provides an explicit alternative: 'Use manage-contact action=search instead when you specifically need entries from your personal contact store only.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare idempotentHint=true, and description explicitly states 'idempotent — safe to retry', adding context. It details the effect of each action (toggles isRead, sets/clears flag, marks complete). No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single paragraph of about 5 sentences, informative but could be more structured with bullet points or shorter sentences. However, no unnecessary information is present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description mentions 'Returns status confirmation per message', which is sufficient. It covers all actions and parameters completely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant meaning beyond the input schema: it explains which actions use which parameters (e.g., dueDateTime only for flag, ids for batch flag/unflag/complete) and clarifies that id is required for mark-read/mark-unread. Schema coverage is 100% but description still adds value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it updates message state without modifying content. The verb 'Update' along with specific actions (mark-read, unflag, etc.) precisely indicates what the tool does. It distinguishes from sibling tools like 'read-email' or 'send-email'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description provides specific guidance on when to use each action and which parameters are required (e.g., id for mark-read/mark-unread, ids for batch flag operations). It mentions batch efficiency but lacks explicit when-not-to-use or references to alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses idempotency (safe to retry), PATCH-style merging with existing state, and return behavior for set actions. This goes beyond the annotations' idempotentHint and readOnlyHint, adding valuable context about how updates behave and what the agent can expect.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-organized, starting with the primary purpose and idempotency note, then breaking down each action with its relevant parameters. It is long but every sentence contributes useful information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 12 parameters, 3 actions, and no output schema, the description comprehensively covers retrieval with section filtering, configuration of auto-replies and working hours, and return behavior for set actions. It is sufficiently complete for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even with 100% schema coverage, the description adds significant value by mapping parameters to specific actions (e.g., startTime/endTime/daysOfWeek for set-working-hours, enabled/startDateTime/endDateTime for set-auto-replies) and clarifying defaults (action=get). This reduces ambiguity for parameter selection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads or updates mailbox-level settings, with specific sub-actions (get, set-auto-replies, set-working-hours). This distinguishes it from sibling tools like search-emails or list-events, which handle different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use each action (e.g., action=get to retrieve settings, action=set-auto-replies for out-of-office), but does not explicitly mention alternatives or when not to use this tool. It lacks explicit exclusions, but the tool's purpose is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (destructiveHint: true), description explains that it sends external comms, subject to rate limits and recipient allowlist, and that calls outside allowlist fail before Graph request. Provides detailed safety control behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single paragraph but well-structured with core purpose first. Contains multiple pieces of information but each is relevant. Could be slightly more concise, but overall effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 9 parameters and no output schema, description covers safety, rate limits, allowlist, alternatives, parameter usage, and return value. Complete for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage, so baseline is 3. Description adds value by explaining interaction of dryRun and checkRecipients, accepting both string and array inputs, and describing return value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it composes and sends an email immediately, notes it is destructive, and returns confirmation with an id. It distinguishes from sibling 'draft' by specifying that for multi-step workflows draft is preferred.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use (immediate send with safety controls) and when not to (prefer draft for multi-step compose/review). Mentions alternatives like 'get-mail-tips' and provides specific usage for dryRun and checkRecipients.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond annotations: it specifies the endpoint (Graph rooms), read-only behavior is reinforced, and it reveals M365-only limitation and outputVerbosity impact. This gives useful behavioral insights not present in the readOnlyHint annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (three sentences) and front-loaded with purpose, then return fields, filtering, and caveats. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, and read-only annotation, the description covers purpose, return fields, filtering semantics, platform limitation, and output verbosity. It provides enough context for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds semantic value by explaining that query matches name/email, capacity is 'minimum', and outputVerbosity controls field count. These clarifications go beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool discovers bookable meeting rooms via the Graph rooms endpoint, with a specific verb ('Discover') and resource ('meeting rooms'). It also distinguishes itself from siblings by focusing on room discovery and explicitly notes suitability for piping into create-event, which differentiates it from other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance: it mentions piping into create-event as attendees and provides filtering options (query, building, floor, capacity). It also includes an exclusion scenario ('Returns empty list on personal accounts'), which serves as a when-not-to-use note.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description reveals that despite using POST, the operation is read-only and requires no additional permissions ('uses the existing Mail.Read scope — no extra permissions'). It also details what the tool returns (automatic replies, mailbox full status, custom tips, etc.), adding behavioral context not present in annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured: it starts with the core purpose and Graph endpoint, then details return contents, usage guidance, and parameter behavior. Every sentence provides useful information without redundancy or fluff, making it concise yet comprehensive.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 params, no output schema), the description covers all essential context: what it does, when to use it, alternatives, parameter formats, default behavior, and the types of tips returned. It fully prepares an agent to use the tool correctly without needing additional external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage of both parameters, including detailed descriptions. The description adds value by explaining the dual input format ('Accepts either a comma-separated string or an array of addresses') and the default behavior of tipTypes ('defaults to all'), which goes beyond the schema's static descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'Pre-send recipient validation via Graph POST /me/getMailTips' and distinguishes it from siblings like send-email and draft by framing it as a pre-check. It names the resource and the exact operation, making it unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'Use ahead of send-email or draft action=create to catch issues like OOO replies or external-recipient warnings before the message goes out.' It also mentions an alternative: 'send-email/draft accept checkRecipients: true to invoke this automatically,' providing clear guidance on when to use this tool vs relying on built-in checks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description openly discloses destructive behavior ('destructive: covers `delete` action', 'permanently removes the contact') and patch semantics ('only fields passed are changed'). It also explains pagination behavior, default result counts, and output verbosity, adding substantial context beyond the annotations' destructiveHint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured, covering all six actions in a logical order with defaults and side effects. Every sentence contributes needed information; there is no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 16 parameters, no output schema, and a wide CRUD range, the description is remarkably complete. It covers action semantics, defaults, pagination, destructive behavior, and alternative tools, leaving virtually no ambiguity for an agent deciding to invoke it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for every parameter. The description adds action-specific meaning (which params apply to which action), clarifies defaults, and notes that the first email entry is primary and that displayName combines with lastName when not provided. This enriches the schema descriptions, though some grouping of params by action is only implicit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource: 'Full CRUD over the signed-in user's personal Outlook contacts'. It clearly defines the tool's scope and distinguishes it from the sibling 'search-people' tool by noting this tool only searches the personal contact store.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit action-by-action usage (list, search, get, create, update, delete) with defaults and parameter applicability. States when to prefer the alternative 'search-people' for cross-source relevance ranking, giving clear when-to-use vs. when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond the minimal annotations: auto-refresh of expired access tokens within a ~90-day window, token persistence to a specific file across restarts, the need to run a local server for browser auth, and the effect of `force: true` on an existing session. There is no contradiction with the annotations (readOnlyHint=false, destructiveHint=false).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but every sentence earns its place, covering all four actions, defaults, prerequisites, and persistence in a compact, logically ordered paragraph. It uses semicolons and clauses to group related information, making it dense but not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a multi-action auth tool with no output schema, the description is remarkably complete. It describes what each action returns or does, prerequisites (npm run auth-server), failure/success flow (device-code-complete after browser entry), and persistence behavior. The agent has enough context to use the tool correctly without external documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description enhances the schema by stating defaults (`action=status`, `method=device-code`), explaining the behavior tied to `force`, and describing the distinct outcomes of each `action` value. It also clarifies the meaning of `method` options (headless vs. local server), adding value beyond raw parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Manage authentication with the Microsoft Graph API' and enumerates the four specific actions (status, authenticate, device-code-complete, about). It is easily distinguishable from the sibling email/calendar tools, and the action list gives a precise map of what the tool accomplishes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent when to use this tool: 'call this first to check before other tools.' It also gives conditional guidance for each action—e.g., use device-code for headless environments, run `npm run auth-server` before using the browser method, and call device-code-complete after the user enters the code. This is strong, actionable usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses that attendees receive invitations on save, returns id/webLink/online-meeting URL, and explains timezone behavior (omit Z suffix for local time). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core action, then provides key details in two additional sentences. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description covers return values (id, webLink, online-meeting URL). Timezone and attendee behavior are explained. With rich schema and annotations, the description is fully adequate for correct tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions. The description adds extra context: attendees trigger invitations, timezone override via environment variable, and the Z suffix convention, enhancing understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Create a new calendar event on the signed-in user's default calendar', clearly identifying the verb and resource. It distinguishes from sibling tools like manage-event which handles updates and cancellations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance: 'Use manage-event action=update to modify... or manage-event action=cancel/delete to remove it'. It also explains timezone handling with a default and override option.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that `delete` does not untag existing messages, provides color preset examples, and clarifies required/optional parameters per action. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Efficiently packed with information in a single paragraph, clearly separating actions with bullet-like clarity. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all actions and parameters, explains output for `list`, notes relationship to sibling tool, and includes deprecation warnings. Comprehensive given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds meaning beyond schema by describing action semantics, color mapping, parameter dependencies (e.g., `displayName` required for create), and deprecation of `categoryId`.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it manages the master category list (colour-coded labels) with specific actions (list, create, update, delete). It distinguishes from the sibling tool `apply-category` which handles tagging/untagging of messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly explains when to use each action, defaults to `list`, notes deprecated alias `set` for update, and points to `apply-category` for message-level operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![outlook-assistant MCP server](https://glama.ai/mcp/servers/littlebearapps/outlook-assistant/badges/card.svg)](https://glama.ai/mcp/servers/littlebearapps/outlook-assistant)

Score Badge

Copy to your README.md:

[![outlook-assistant MCP server](https://glama.ai/mcp/servers/littlebearapps/outlook-assistant/badges/score.svg)](https://glama.ai/mcp/servers/littlebearapps/outlook-assistant)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/littlebearapps/outlook-assistant'

If you have feedback or need assistance with the MCP directory API, please join our Discord server