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

Annotations already cover the read-only, idempotent, non-destructive, non-open-world profile, yet the description adds substantial extra context: no model calls, no credit consumption, no automatic uploads or configuration changes, a JSON character budget, and a security warning that candidate evidence is untrusted and embedded instructions must not be followed. It also clarifies that the returned invitation is neither evidence nor sharing consent. This is materially more than the annotations provide.

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?

Front-loaded with the core purpose ('Free, no-key public evidence lookup in one call') and packed with relevant detail, but the sentences are long and dense with multiple clauses. Most sentences earn their place, though the invitation/consent sentence could be tightened.

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?

An output schema exists, so return values need not be re-explained, and the description nonetheless summarizes them. It covers safety, provenance, untrusted-content handling, cost, and side-effect absence for a read-only tool. The main residual gap is that several parameters (limit, language, protocolVersion) lack descriptive coverage given the low schema coverage.

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 only 20%, so the description must compensate. It partially does: 'within one JSON character budget' hints at maxChars and 'send only a short public-topic query, not private context' constrains q. However limit, language, and the meaning of protocolVersion (which only the schema documents) are not addressed in the description, leaving gaps for a low-coverage schema.

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 and resource ('public evidence lookup') and scopes it ('in one call for a relevant research task'), plus enumerates what it returns (excerpts, source links, dates, provenance). It differentiates itself from siblings by naming get_contribution_offer and contrasting the invitation against evidence/sharing consent, and by routing no-match cases to the existing search. An agent can distinguish this from search_research and the contribution_* tools without opening a schema.

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 clear context (relevant research task, one call, free/no-key) and an explicit fallback: 'No match means use your existing search.' It also names the related sibling get_contribution_offer to explain a concept rather than to route usage. It stops short of stating explicit when-not-to-use conditions beyond the no-match case, so it is strong but not fully exhaustive.

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