collect_digests

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

With no annotations, the description fully bears the burden of behavioral disclosure. It explains the return value (short digest per worker plus on-disk path), implies it is a read-only operation ('Gather... from a finished research batch'), and mentions no destructive side effects. It could add details about required permissions or error handling, but is adequate.

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 concise: three sentences plus an 'Args' section. It front-loads the purpose, each sentence adds value, and there is no extraneous 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?

Given the presence of an output schema and sibling tools, the description adequately explains what the tool does, when to use it, and what it returns. It implies the batch must be finished, which is clear enough, but could explicitly mention that the batch must be completed.

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 0%, so the description must compensate. It explains that batch_id is the ID returned by research_fanout and that include_stderr, when true, includes stderr for debugging. This adds meaningful context beyond the schema's basic 'Batch Id' and 'Include Stderr' titles.

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 'Gather the stdout digests from a finished research batch (NOT the full reports)', specifying the verb 'gather', the resource 'stdout digests', and the scope 'finished research batch'. It explicitly distinguishes from full reports, helping differentiate from sibling tools like research_fanout.

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 explains when to use the tool: after a finished batch, to keep context lean, and suggests reading individual subreport files only when needed. It implies not to use it for full reports, but does not explicitly name alternatives or state when not to use it.

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