Read document metadata

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so excellently. It reveals a surprising implementation detail: that xlsx metadata is read via a throwaway xlsx-to-pdf preview, which may affect performance or side effects. It also notes that odf is a standalone formula document, giving the agent insight into internal handling. This exceeds expectations by offering transparency beyond simple 'reads metadata'.

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 sentence but efficiently packed with information. It front-loads the main purpose and then adds relevant edge-case details in a parenthetical. Every word earns its place; no fluff or redundancy. It is concise and well-structured.

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 moderate complexity (multiple formats, edge cases) and the absence of annotations and output schema, the description is remarkably complete. It covers the tool's scope, special behaviors (xlsx via preview, odf as standalone), and implicitly clarifies what fields are read. The only minor gap is not detailing the exact return structure, but without an output schema, this is acceptable. This is a high-quality description.

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 schema covers 100% of the parameter descriptions, so the baseline is 3. The description adds value by explicitly listing the metadata fields read (title, author, subject, keywords, creator, producer, timestamps), which clarifies what the output may contain, even though there is no output schema. This additional semantic detail justifies a 4.

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: reading a document's own metadata fields (title, author, subject, keywords, creator, producer, timestamps). The verb 'reads' and the specific resource 'document metadata' are precise and differentiate it from siblings like metadata_write and outline_document. It also explicitly notes format coverage, including edge cases (xlsx, odf), which further distinguishes it from potential alternatives.

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 clear context on when to use this tool: for reading a document's own metadata across supported formats. It does not explicitly list when not to use it or mention alternatives like metadata_write for setting metadata, but the context is clear enough for an agent to infer that this is for reading. Since there is no explicit exclusion or alternative guidance, the score is 4 rather than 5.

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