Who talks about

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description usefully adds that results are ranked by frequency and include earliest mention plus a top tweet, but it omits the behaviorally important fact that results come from a bounded scan (max 5000 tweets), which affects how complete the answer is.

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?

A single front-loaded sentence that leads with the core verb and resource, then the ranking and outputs. No filler, though 'best-received tweet' is slightly vague for a one-sentence budget.

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?

Seven parameters with under half documented in schema and no output schema, yet the description explains none of the tuning knobs. An agent could call it correctly on `q` alone but has no basis for setting scan/top or for interpreting the bounded-scan caveat.

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 only 43%, so the description must compensate for 'top', 'scan', 'from_user', and 'reply_to_user' — and it does not. 'scan' is especially opaque (it caps how many tweets are examined) and is decisive for interpreting result completeness; neither its meaning nor 'top''s is clarified here.

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 ('Find people ... authors who tweet about a word or phrase') and even previews the ranking and returned artifacts (earliest mention, best-received tweet). It does not distinguish itself from the similarly named sibling ca_find_people, so an agent could plausibly confuse the two.

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 phrase 'Find people by topic' implies a discovery/influencer-identification use case, but the description never says when to prefer it over ca_find_people, ca_search_tweets, or ca_first_said. No exclusions or prerequisites are stated.

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