Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses that the tool never sends, that sending is manual in Outlook, that body replaces Graph's quoted original, and that the draft lands in Drafts. It omits failure/permission behavior and what happens to existing settings, but the safety profile is unusually well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and the critical 'NEVER sends' constraint before the conditional detail. Three sentences, each earning its place, though 'Otherwise a new standalone draft is created' is mildly redundant given the opening.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a create tool with no output schema and no annotations, the description covers the important behavioral and branching facts. It stops short of indicating what the call returns (e.g., a draft identifier), which no structured field supplies, but otherwise an agent has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 goes beyond the schema by explaining the semantics of replyToMessageId (threaded reply, quotes original) and the interaction where a provided body overrides that quoted original — meaning that is genuinely additive, not a restatement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create a draft email in the user's Drafts folder') and immediately constrains scope with 'NEVER sends', making it unmistakably distinct from the read-only siblings (read_email, list_emails, search_emails). An agent can differentiate it from every sibling without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description sets a clear context (composing a draft the user will send manually) and spells out two conditional branches: reply-to threading when replyToMessageId is set, standalone otherwise. It does not name an alternative tool, but no sibling performs a comparable write, so there is little to exclude against.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the return shape ('compact JSON array of message summaries'), but omits pagination behavior, permission/auth requirements, and whether an empty folder returns an empty array or an error.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the primary action, then filters, then the return format and follow-up call. Every sentence earns its place with no padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter, filter-based list tool with no output schema and no annotations, the description covers purpose, filtering scope, return shape, and the next step in the workflow. Remaining gaps (pagination, auth, empty-result behavior) are modest for a read-only lister.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters thoroughly (defaults, max, ISO-8601 format, folder names, 404 behavior). The description's paraphrase ('sender substring') is actually looser than the schema's precise 'STARTS WITH' semantics, adding no meaning beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List emails from a mail folder') plus the scope of optional filters, and names the sibling tool (read_email) that handles full content. An agent can distinguish it from read_email and search_emails without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes in the retrieval workflow: use read_email with a returned id to fetch full content, which clarifies that this tool yields summaries, not bodies. It stops short of an explicit when-to-use-this vs search_emails rule (that guidance only lives in the schema for the 'from' parameter).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden, and it does disclose real behavioral traits: recursion is limited to one level deep, the scoping depends on whether parentFolderId is present, and the 'id' field in the response is the folder reference. It stops short of covering permissions, pagination behavior against the limit parameter, or response shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences, front-loaded with the core behavior, then the id-for-list_emails tip, then the well-known-names shortcut. Every sentence carries information; slight redundancy between the descriptions of parentFolderId here and in the schema keeps it from being maximally tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the necessary work of noting that the returned 'id' is the folder reference to reuse, and with no annotations it covers scoping and depth. It does not address the limit parameter's interaction (e.g., truncation of results in large mailboxes), which is the main remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3 and the schema already documents both parameters. The description still adds meaning: it clarifies the depth semantics ('immediate child folders, one level deep') rather than just 'children', and it enumerates the valid well-known folder name values, which the schema does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List mail folders') and immediately splits the behavior by input: no parentFolderId returns top-level folders, parentFolderId returns immediate children. It also distinguishes itself from siblings by naming list_emails as the consumer of the returned id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent when NOT to call it: Outlook's well-known folder names (inbox, drafts, sentitems, etc.) can be passed directly to other tools without calling list_folders first. This is a genuine routing rule against an alternative path, not just a use-case hint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses output behavior (JSON, body as plain text, attachments returned as metadata only, implying save_attachment is needed to get file bytes), but says nothing about permissions, size/truncation limits, or error behavior for invalid ids.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tightly written sentence with a parenthetical that carries real information (attachment metadata vs. disk write, plain-text body). No filler, and the core action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description covers the essentials: what is returned, that attachments are metadata-only, and where to go for file content. It is a bit thin on failure modes and whether the body can be omitted via includeBody, but nothing critical is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including the messageId provenance ('returned by list_emails or search_emails') and includeBody's default and text-over-HTML preference. The description adds the 'plain text' return hint but no new parameter detail, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Fetch) and resource (one email message) with the identifier (id) and an additional scope note about attachments. It is clearly distinguishable from siblings list_emails and search_emails, which enumerate rather than fetch a single message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context (a single message, found via an id from list_emails/search_emails per the schema) and routes attachment retrieval to save_attachment, an explicit alternative. It stops short of stating when to prefer this over searching or when not to use it, so it is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description carries the full behavior burden and handles it well: it discloses the filesystem write side effect, the confinement to the server's allowed directory, the non-overwrite policy with the ' (2)', ' (3)' renaming scheme, and the return value. What is missing is auth/permission requirements and failure modes (oversized attachments, missing IDs).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the action and resource, then side effects, then return value. No filler, and the overwrite-avoidance detail is stated before the return contract where an agent would want it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter mutation tool with no output schema and no annotations, the description covers what an agent needs: the write target directory, the collision-handling rule, and the return value (absolute path). The only omission — error behavior — is minor for this operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — all three parameters, including the targetFilename constraints and the non-LLM-controllable destination directory, are fully documented in the schema. The description adds only marginal framing ("one attachment", "default ~/Downloads/outlook-mcp/"), so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource ("Download one attachment from a message and save it to the local filesystem") with clear scope — exactly one attachment per call, written to disk. This is cleanly distinguishable from the read-only siblings (read_email, list_emails, search_emails), which retrieve content but do not persist it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the phrasing (extract an attachment to disk), and the schema notes that attachmentId comes from read_email's attachments list, which hints at the workflow. However, the description itself names no alternatives and states no when-not conditions — e.g. whether it works for inline images or whether read_email is sufficient when you don't need the bytes on disk.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well: it discloses relevance-based ranking (not date-sorted), that received: filters are honored on AAD but IGNORED on the personal backend, automatic backend selection, and the return shape. These are non-obvious behavioral quirks an agent must know to call correctly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause and each sentence carries useful information (operators, account behavior, ranking, alternative). The single dense paragraph of intertwined caveats is slightly heavy but nearly all of it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description explains the return format (compact JSON array of hits with message IDs usable by read_email), and it covers the query syntax and cross-account pitfalls. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds query semantics beyond the schema: additional operators (hasAttachment:true, body:, quoted phrases, AND/OR) and the critical caveat about date-operator behavior per backend. It does not, however, add anything for the limit parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Full-text search across the user's ENTIRE mailbox') and scopes it explicitly (all folders, all years), which separates it from the folder-scoped list_emails sibling. An agent can identify the tool's job without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the alternative ('use list_emails (folder-scoped) with since/until') and the exact condition that selects it (need for strict date filtering). It also clarifies cross-account behavior so the agent knows when results may be date-unreliable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.