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

Annotations only supply readOnlyHint and openWorldHint, so the description carries the real behavioral burden and delivers: matching is literal substring, all word forms must be supplied in a single call, results are capped at 3 excerpts per item, links deep-link to the exact second, and non-Pro tiers inherit the opinions historyFrom window. These are non-obvious operational constraints an agent could not infer from structured data.

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 purpose and scope before drifting into variant-spelling examples and tier caveats. The example lists are dense and the final sentence about historyFrom arrives late, but every sentence carries operational information rather than 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?

There is no output schema, and the description compensates by describing the result shape (influencer, title, publish time, extracted stock calls, up to 3 timestamped excerpts) plus the instruction to quote excerpts with their link because they are partial. Nothing needed to call or interpret this tool is missing.

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 already 86%, so the baseline is 3, but the description meaningfully extends it by explaining how to populate `terms` (every spelling form in one call, with worked examples like 费半/SOX/SOXX and Simplified vs Traditional) and by clarifying the return-shaping role of `context`. It leaves `from`/`to`/`limit` formatting largely to the schema, and references a historyFrom that is not itself a parameter.

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 (search) and a precisely scoped resource (full transcript/post text across all tracked influencers, newest first), and immediately distinguishes itself from the sibling stock_opinions/latest_opinions by framing it as 'anything beyond the extracted stock opinions.' An agent can route between this and the opinion tools without opening either 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 an explicit when-to-use rule ('anything beyond the extracted stock opinions') plus concrete triggering cases: indexes and sectors, macro, rates, market views, passing stock mentions. It also sets the counter-expectation that literal substring matching is in play, so the agent knows when this tool will and will not return useful hits.

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