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

Annotations already cover read-only, idempotent, non-destructive behavior, but the description adds substantial context: dropped terms, wildcard expansions, warnings content, return summaries by year/community, nearest broader query, quote_id handoff, and account/payment requirements.

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 dense but front-loaded with purpose and syntax, and every clause carries information. It could be more structured for readability, but there is no significant filler.

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?

With no output schema and only two parameters, the description fully explains the return values, warnings payload, quote_id handoff to lab_run, and account/payment prerequisites. An agent has enough to invoke it correctly.

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, but the description adds valuable query syntax and examples beyond what the schema provides. The markdown alternative parameter is left to the schema, keeping this below a 5.

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, resource, and scope: 'Scope a multi-term question with a boolean filter' over element symbols/names and exact topic names. The syntax and the lab_run handoff make it clearly distinguishable from execution siblings.

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 practical guidance: read `warnings` first, narrow filters (two elements + one topic) work best, and lab_run turns quote_id into ranked papers. It lacks an explicit when-not-use comparison against research/search_subjects, but the intended workflow is clear.

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