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

The description adds value beyond annotations: it explicitly states that only metadata is returned and 'no document text' is served. This prevents an agent from expecting the document content, which is a behavioral trait not captured by the readOnlyHint or idempotentHint annotations. Annotations provide the safety profile, but the description adds the return-scope constraint.

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 concise sentences, each earning its place. The first states the purpose and the resource, the second explicitly limits the output to metadata. No fluff, no repetition of schema info. It is front-loaded with the core action and resource.

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 tool is simple with a single parameter, fully described in the schema, and the description clarifies the metadata-only scope. With annotations covering safety and idempotency, and no output schema to explain, nothing critical is missing. It could benefit from mentioning the output format (e.g., JSON), but that is not essential for a metadata-only read 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?

The schema has 100% coverage with a description for document_id, so the baseline is 3. The description adds crucial context: it explains the document_id comes from a get_case_docket entry's document_id field, which the agent might not know from the schema alone, and reaffirms that only metadata is returned. This enhances the parameter semantics.

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 verb ('get'), a clear resource ('docket document'), and the identifying field ('by its Docket Nexus document id'). It lists the types of metadata returned, which distinguishes it from sibling tools that handle cases or companies. It clearly differentiates itself from get_case_docket (which retrieves an entry list) by focusing on a single document's metadata.

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 implies it is used when you have a document_id from a docket entry, as the parameter description says 'as returned in a get_case_docket entry's document_id field'. It does not explicitly state when not to use it, but the focus on a single document and metadata-only makes that clear. No alternatives are named, but the context makes the use case apparent.

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