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

Annotations already indicate destructive behavior, but the description adds important context: atomicity, exact replacement matching, SHA requirement, and explicit forbidden actions (delete, config, links, credentials).

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?

Concise single paragraph that front-loads the core purpose and then efficiently covers SHA, workspace_id, and limitations without unnecessary detail.

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?

Covers creation vs. editing, SHA requirements, workspace_id, and limitations; with no output schema, return values need no explanation, though failure behavior on non-unique replacements could be mentioned.

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 covers 60% of parameters with descriptions; the tool description clarifies replacement uniqueness, SHA acquisition, and workspace_id usage, though it adds little for the obvious path 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 (create/edit) and resource (UTF-8 file), clearly distinguishing from siblings by noting exact replacements, SHA-256, and forbidden operations like deletion or credential access.

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?

Provides practical guidance on obtaining the SHA via workspace or file_info, workspace_id handling, and constraints, but does not explicitly name an alternative like write_file.

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?

The description goes beyond the annotations by mentioning that job_cancel terminates the owned worker process tree, that external extension code requires exact-hash local approval, and that globally authorized actions must be enabled. This adds meaningful safety context beyond the destructiveHint and readOnlyHint annotations.

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?

The description is somewhat dense and list-like, but it is still focused and each sentence contributes necessary information about actions, job handling, or authorization. It could be organized into clearer bullets, but it is far from bloated or redundant.

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?

Given the tool's complexity—8 parameters, multiple actions, job lifecycle, and extension authorization—the description covers the essential operational context. It lacks explicit output format details, but no output schema is provided, and the action-specific behavior is sufficiently described for an agent to invoke the tool 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 already high at 88%, and the description adds useful semantic relationships, such as job_id being returned by an explicit or auto-promoted Job action and workspace_id being required for workspace-bound operations when multiple workspaces are configured. This clarifies parameter behavior beyond the raw schema.

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?

The description clearly identifies this as a stable extension gateway and enumerates the exact actions (list, info, run, job_list, job_status, job_cancel). It also distinguishes the tool from ordinary file operations by noting that installing more extensions does not add MCP tool names, making its role unambiguous.

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 provides practical guidance on how to use the tool: it explains the purpose of each action, how long foreground actions can be promoted to jobs, and that extension code requires approval. It does not explicitly mention competing alternatives, but it gives enough context for an agent to decide when this gateway is the appropriate entry point.

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?

Annotations already indicate read-only and non-destructive behavior. The description adds that bytes are not exposed and mentions shared workspace/link/sensitive-path policies, providing extra context 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.

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

The description is two sentences, tightly packed with essential information: function, limitation, use case, and policy alignment. No fluff or redundancy.

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 simple metadata/hash tool, the description covers key aspects: what it returns, what it avoids, and when to use it. The absence of an output schema is compensated by the clear explanation of the return value. It is complete enough 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 descriptions cover workspace_id but not path, giving 50% coverage. The description does not add any parameter details, but the parameters are simple and self-explanatory (path, workspace_id). This is adequate but not enhanced.

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?

The description clearly states it returns metadata and SHA-256 for a regular file, and explicitly notes it does not expose bytes, distinguishing it from content-reading tools. The phrase 'use this SHA before editing large text files' gives a concrete purpose and workflow.

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?

It provides a specific use case ('use this SHA before editing large text files') and clarifies the tool's non-content nature. While it doesn't compare directly to sibling tools, the 'without exposing its bytes' phrase implies when not to use it, giving adequate guidance.

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?

The description discloses critical behaviors beyond the destructiveHint annotation: it denies links, credentials, dependencies, and protected writes; explains no-clobber default with overwrite requiring SHA-256; and describes cross-volume move fallback. These specifics are valuable safety context not present in 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.

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

The description is compact and front-loaded, leading with the core purpose and then detailing constraints. It avoids unnecessary words and presents information in a logical flow, though it could benefit from a clear separation of parameter usage from general behavior.

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 tool with 10 parameters, no output schema, and moderate complexity, the description covers important safety and overwrite aspects but omits explanations for max_bytes, create_parents, expected_source_sha256 usage, and action semantics. These gaps could lead to incorrect invocation, especially for a file operation tool.

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?

The description adds meaning for workspace IDs, overwrite requirements, and no-clobber default, which helps with parameters lacking schema descriptions. However, it does not explain max_bytes limits, create_parents behavior, or the action enum values, leaving gaps despite the low schema coverage of 40%. It partially compensates but not fully.

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?

The description states the exact operation (copy/move) on a single regular file, with workspace confinement. It clearly distinguishes from edit/write operations and sets expectations about scope. The phrasing 'Core FolderBridge regular-file copy/move' is specific and actionable.

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 provides parameter-level guidance (workspace IDs, overwrite behavior) but does not explicitly indicate when to choose this tool over siblings like edit_file or write_file. There is no mention of conditions for selecting this tool or exclusions for other operations, leaving tool selection to inference.

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?

Discloses retention limits (15 minutes, 20 MiB), recording of MCP/Tunnel metadata, bounded redacted diagnostics, and explicitly states it never stores full request/response bodies, going beyond the read-only annotation.

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?

Two concise sentences, first summarizing the tool's purpose and data characteristics, second giving actionable usage for actions; no unnecessary fluff.

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?

Lacks explanation of parameters like role, limit, minutes, and their interaction; while the action usage is covered, the tool cannot be fully used without inferring parameter meanings from the schema.

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?

Description does not explain any of the parameters (action, role, limit, minutes) except implicitly mentioning action usage; schema has enums and defaults but description adds no parameter definitions.

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 the verb 'Read' and the resource 'FolderBridge's compact local reliability flight recorder' clearly, distinguishing it from other read tools like server_info or file_info by specifying the domain.

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?

Provides guidance on which action to use (status, recent, errors) but does not compare with sibling tools or explain when to choose this over others; still, the action-specific advice is useful.

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?

The description adds meaningful behavior beyond the annotations: it states supported formats, the 'bounded' size constraint, and that the archive is never extracted to disk. These are useful operational details that the readOnlyHint annotation does not convey.

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?

Two sentences, front-loaded with the return value and formats, and the key behavioral guarantee is stated in one short second sentence. Every word 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?

The description explains the return form (MCP image content), supported formats, and the two input paths, which is sufficient for an agent to call the tool correctly. It does not describe error cases, but the schema and annotations cover the essential requirements.

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 four parameters. The description adds context about the two usage modes but does not go beyond the schema's mutual-exclusion notes or parameter meaning.

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?

The description uses a specific verb ('Return') and a precise resource: one bounded PNG/JPEG/GIF/WebP as MCP image content. It also clearly distinguishes the two input modes (direct path vs. ZIP member), which separates this tool from sibling file operations.

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 gives clear context for when to use the tool: when you need an image as MCP content, either from a workspace path or from a ZIP member. It does not explicitly name alternative tools or exclusion criteria, but the direct-vs-archive distinction is actionable.

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?

The description explicitly discloses safety-relevant behavior: it does not execute macros, embedded objects, or workspace code. This goes beyond the readOnly/destructive annotations and reassures the agent about side effects.

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?

The description is compact and well structured: a safety-and-method sentence, a returns list, and a non-execution guarantee. Every sentence adds meaningful information without redundancy.

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 return-value list is helpful, and the safety behavior is clear. However, the description omits parameter semantics and does not fully explain how page_start/page_end affect inspection, leaving noticeable gaps for a four-parameter tool.

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 only 25% and the description does not explain path, page_start, or page_end. Only workspace_id is described in the schema; the description adds no parameter-level clarification, leaving the agent to guess meanings and ranges.

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?

The description states a specific action ('inspect a PPTX') and resource, and lists concrete outputs ('slide text, diagram-to-slide mappings, dgm:pt points...'). It is clearly differentiated from the sibling tools by its OOXML/SmartArt focus.

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?

No guidance is given on when to use this tool versus alternatives such as file_info or image_open. It implies use for PPTX inspection but does not explicitly state selection criteria or exclusions.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, which the description aligns with by using the non-destructive verb 'List'. The description adds useful specificity about what information is returned, going beyond the annotations. No contradictions are present.

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?

The description is a single, concise sentence that lists the exact outputs. It is well-structured and front-loaded with the action verb, making it easy to understand at a glance. No unnecessary words or complexity.

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?

Given that there is no output schema, the description adequately informs the agent of what the tool returns: fixed workspace IDs, enabled capabilities, approved tasks, and safety boundary. This is sufficient for understanding the tool's result without needing additional details.

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?

The tool has zero parameters, and the input schema is fully covered with an empty properties object. Since there are no parameters to describe, the baseline of 4 applies. The description does not need to explain parameters because there are none.

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?

The description clearly states the tool's purpose with a specific verb 'List' and identifies the exact resources it returns: workspace IDs, capabilities, approved tasks, and safety boundary. This makes the tool's function unambiguous and distinct from typical file or workspace operations.

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 does not provide any guidance on when to use this tool versus its siblings. While it is clearly a read-only status tool, it does not explicitly state that it should be used for checking workspace safety before operations, nor does it mention alternatives. Thus, usage context is implied but not explicitly stated.

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?

Annotations already mark readOnlyHint=true, and the description is consistent with that while adding behaviors beyond it: literal (not regex) UTF-8-only searches, streaming/paging for large files, and denied content categories. 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.

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

Three front-loaded sentences: action capabilities first, workspace_id routing second, path/denial constraints third. No filler; every sentence carries operational information.

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 9-parameter, five-action tool with no output schema, the description covers the action space, key routing, and constraints well. It does not specify output shapes or per-action result semantics, but the action names themselves make the expected results reasonably clear.

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?

With 56% schema coverage, the description adds meaning to several parameters: workspace_id's source and trigger, path's relative-base convention, query's literal-search nature, and limit/offset's page semantics. It does not expand on max_results or case_sensitive, but those are named and defaulted in the schema.

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?

The description names explicit actions — list, read, search, status, diff — with concrete resource and scope (files, UTF-8 text, git output). This distinguishes it from sibling tools like file_info and edit_file by making clear it is a broad read-only workspace inspection surface.

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?

It gives a clear context for use: multi-workspace routing via server_info, relative paths, and a hard denial list (links, credentials, dependencies, VCS internals). It does not explicitly name sibling tools or say when to prefer file_info or edit_file, so it stops short of full alternative guidance.

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?

Annotations only supply the generic destructive/idempotent profile; the description adds substantive traits beyond them: staging lives outside the workspace, replace mode rechecks the original target SHA at commit, abort discards staging, and commit is a same-directory fsync plus atomic replace. The offset-based non-duplicating retry guarantee is also stated.

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 dense sentences that lead with the transaction model, then the action sequence, then the durability and safety guarantees. Nothing is repetitive of the name or title, and every clause carries operational information.

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 10-parameter, multi-action tool with no output schema, the description covers the full lifecycle and the return of transaction_id is captured in the schema itself. It leaves unstated what status or commit return on success and what happens when an offset mismatch or commit-contract failure occurs.

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 90%, so per-parameter documentation is already strong (baseline 3). The description goes further by binding parameters to actions as a cross-field contract: commit needs the complete expected size and SHA-256, append needs the exact next byte offset, and replace mode requires the original target SHA. It doesn't add format examples for the hashes, which the schema already constrains.

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 with scope: a host-owned five-action transaction for large whole-file creates or replacements. The 'whole-file ... without requiring one giant MCP message' framing distinguishes it from the sibling edit_file, which handles partial edits.

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 explicit protocol sequencing (begin, one or more appends, optionally status, commit, abort) and the size/whole-file condition that motivates it. It stops short of naming edit_file as the alternative for small or partial changes, so the routing decision is implied rather than stated.

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