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

Despite having readOnlyHint, idempotentHint, and destructiveHint annotations, the description adds substantial behavioral context: it clarifies that only metadata is returned, explains the meaning of audit_url and archived_url (including the worker path for streaming bytes), and highlights the staleness signal (canonical_changed_at > last_verified) with an instruction to surface it to users. This goes well 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 structured with clear sections: purpose, context, args, return object, and guidance. Although lengthy, it is efficient because every sentence adds value—especially the return object details, which are necessary given no output schema exists. It is front-loaded with the core purpose.

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 tool with one parameter and no output schema, the description is remarkably complete. It defines the return object with types and comments, explains the two URL fields, and provides actionable staleness logic. It also gives context on how source_ids are obtained, making the tool self-contained.

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 input schema has no description for source_id (0% coverage), so the description carries the burden. It explains source_id is an integer and required, and elaborates on its meaning by explaining where source IDs come from. It doesn't mention constraints like minimum value (already in schema) but fully compensates for the missing schema description.

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 opens with a specific verb+resource: 'Return provenance metadata for one source by integer source_id.' It clearly distinguishes from siblings by stating it returns metadata only, not document content, and lists specific source types. It also explains where source IDs are surfaced, making the tool's 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 clear context on when to use this tool (when you have a source_id from citations, reference lists, etc.) and what it does not do ('not the document content'). However, it does not explicitly name alternative tools for fetching content, so it stops short of explicit when/when-not guidance.

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