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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, non-idempotent, non-destructive) by disclosing cost (~$0.0155 per live Google search, free when web_search=false), that every web candidate is fetched and verified, and the semantics of states_figure. It explicitly warns never to cite a page whose states_figure is false.

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?

Purpose is front-loaded in the first clause, and the remaining sentences each carry distinct operational payload (candidate origins, cost, verification semantics, next action, fallback). No filler sentences.

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, the description supplies the missing return semantics (first_party candidates cited with their period, vendor pages, web candidates with states_figure) and the success/failure paths. For a 3-parameter tool with annotations, nothing an agent needs to invoke and interpret it is absent.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond it: web_search=false yields free candidates only and live search costs ~$0.0155 per claim. This ties the boolean flag to a concrete cost trade-off the schema does not express.

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 (find) and resource (sources for the draft's '[SOURCE NEEDED]' markers, unsourced figures/superlatives), plus the scoping detail that candidates are found, never generated. This is clearly distinguishable from siblings like accept_source or assist_draft.

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 the end-to-end workflow: present each claim and candidates to the user, then call accept_source on their choice, and cut/soften the claim if nothing qualifies. It also names web_search=false as the free-only path. It lacks an explicit statement of when this tool should not be used versus other research siblings, so it falls just short of a 5.

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