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

No annotations are supplied, so the description carries the disclosure burden. It does add real context — inputs are auto-detected from path, data URI, base64, or inline content, and the comparison works across formats — but it says nothing about error behavior for unsupported formats, read-allowlist failures, size limits, or cost of large comparisons.

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 in one sentence, then a compact bullet list for the return value. The 'Returns a dictionary with' block partly duplicates the existing output schema, which costs some space, but nothing is padded or verbose.

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 a six-parameter tool with an output schema, the description covers input flexibility, cross-format support, and the shape of the result. Remaining gaps (failure modes for unsupported or oversized documents) are modest for a read-only comparison 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%, so every parameter is already documented in the schema; baseline 3 applies. The description adds only the input auto-detection idea and does not elaborate on format, granularity, context_lines, or ignore_whitespace beyond what the schema states.

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 ('Compare two documents and return their differences') plus a notable capability: cross-format comparison such as DOCX vs its PDF export. It is clearly distinct from the siblings (read_document_as_markdown, search_documents, get_document_outline, list_workspace_files), though it never explicitly names an alternative.

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 only implied by the purpose — an agent infers that this is the tool for 'are these two documents different' questions. There is no explicit when-to-use/when-not guidance, no statement about prerequisites, and no routing advice versus the read/search/outline siblings.

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 supplied, so the description carries the burden and does disclose one non-obvious behavioral trait: returned indices line up with edit_document's '#N' addressing, which is not inferable from the schema. It is silent on failure behavior for unsupported formats or size limits, and the return-value section partly duplicates the existing output schema.

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, then usage, then return shape in a scannable list; no filler sentences. The 'Returns a dictionary with' block is somewhat redundant against the declared output schema, costing a point on tightness.

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 read tool with full schema coverage and an output schema, the description covers purpose, navigation use case, and cross-tool index semantics. Remaining gaps are minor: no note on unsupported formats or how errors surface.

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 doc, max_level, and format_hint are already well documented in the input schema. The description adds no parameter-level meaning (e.g., when to set format_hint or how max_level affects indices), so 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?

States a concrete verb and resource: 'Return the heading structure (table of contents) of a document.' The parenthetical clarifies the concept and the follow-up sentence scopes it to navigation of large documents, which separates it from read_document_as_markdown (full content) and search_documents (query match) without needing 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?

Explicit when-to-use: 'navigate a large document before extracting specific sections,' and it points at a downstream consumer (edit_document's '#N' notation). It stops short of naming an alternative sibling or a case where this tool is the wrong choice, so it is clear context without explicit 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?

With no annotations, the description carries the full burden and does well: it discloses the read-allowlist confinement, that results are absolute and sorted, and that output can be capped via a truncation flag. It omits whether hidden files are included and says nothing about permissions or performance on large trees, so it is strong but not exhaustive.

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 scope constraint, then a usage sentence, then a bulleted return shape — clean and skimmable with no filler. The return-value block is duplicated by the existing output schema, so a chunk of the text is redundant rather than earning 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?

For a zero-required-parameter listing tool this covers the essentials: scope, purpose, allowed follow-up use, and truncation behavior. Since an output schema already exists, the enumerated return fields are surplus, and the description never explains how narrowing by subdirectory or pattern changes the result set.

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 pattern, recursive, and subdirectory are already fully documented with defaults and examples. The description adds no meaning beyond the schema for any of the three parameters, which is the baseline case rather than a value-add.

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 first sentence states a specific verb and resource (list files) plus the governing scope (the read allowlist), and the follow-up frames it as the discovery step preceding reading/editing. That framing makes it immediately distinguishable from read_document_as_markdown and search_documents without opening any 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?

"Use this to discover what is available before reading or editing" gives clear sequencing guidance, and "Paths returned here can be passed directly to the other tools" tells the agent how output feeds siblings. It does not explicitly say when to prefer search_documents over listing (e.g., known filename vs known content), so a small gap remains.

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 supplied, the description carries the full burden and does well: it discloses the read-allowlist constraint on file paths, that image inclusion and markdown flavor are fixed at server startup and cannot be changed per call, and that section matching is case-insensitive. It also describes the response shape (a text content block followed by one image block per image, or alt-text placeholders when include_images=false), which no output schema covers. Only error behavior and size/rate limits are unaddressed.

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 purpose, then formats, then source detection, then optional behaviors, then return shape — a sensible ordering for an agent scanning it. The long format enumeration and the repeated source auto-detection list (already in the schema) are the main slack, but they remain short and skimmable.

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 four-parameter read tool with no annotations and no output schema, the definition covers input handling, configuration constraints, and return structure, which is enough to invoke it correctly. The only meaningful omission is what happens on failure (unreadable file, unsupported format, no matching section).

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 all four parameters are already documented, and the description largely restates the source auto-detection rules and the section heading match. It adds no meaning for pdf_pages or format_hint, which live entirely in the schema, 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 and resource ('Read a document and convert it to Markdown format') plus the full set of supported input formats, so the agent knows exactly what the tool produces. It does not explicitly contrast itself with the closest sibling, get_document_outline, which returns structure rather than full content, so an agent must infer that boundary.

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 rather than stated: the description says you may 'optionally extract a specific section' and explains how the source is auto-detected, which guides parameter choice. It never says when to prefer this over search_documents, diff_documents, or get_document_outline, and gives no exclusions or prerequisites beyond the read-allowlist note.

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 well: it discloses that keyword mode needs the optional rank-bm25 dependency, that grep is stateless, that files are converted to text first, and that hit spans are marked with << >>. It omits permission/allowlist behavior (only in the schema) and any performance or size limits.

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 purpose then structured into modes and return shape; every section is scannable. The return dictionary listing is partly redundant given an output schema exists, which costs a bit of tightness.

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 purpose, mode tradeoffs, format support, and conversion behavior for a 7-parameter search tool. Because an output schema exists, the return-value enumeration is unnecessary, and allowlist scoping is left entirely to 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?

Schema description coverage is 100%, so the baseline is 3. The description corroborates mode semantics and the format support, but adds little parameter meaning beyond what the schema already documents for paths, regex, top_k, and recursive.

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 ('search a corpus of documents and return ranked snippets') and immediately contrasts it with the sibling read tool by explaining it returns passages rather than whole files. An agent can distinguish it from read_document_as_markdown 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?

Gives explicit when-to-use guidance for each mode: keyword for 'find the most relevant passages', grep for 'find every occurrence of X'. It does not explicitly say when to prefer this over list_workspace_files or when a direct read is better, but the mode routing is clear.

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