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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond them, notably that results are deduplicated and cached (so data may be stale) and that this is unweighted discovery evidence. It says nothing about refresh cadence or coverage of the external list, so it does not earn a 4.

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?

Three compact sentences with the core distinction front-loaded and nothing wasted. The final clause about matched_trend_id is slightly dense but carries useful routing 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?

For a one-parameter read tool with no output schema, the description covers the essentials: it characterizes the data as unmeasured labels, warns about caching, and explains the one return field an agent must interpret (matched_trend_id). Only pagination or list-coverage limits are unaddressed.

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?

There is one optional parameter and schema coverage is 100%, so the schema already documents limit, its default of 10, and the 1-25 bound. The description adds no meaning about limit; baseline 3 applies when the schema does the work.

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 ('List labels found in an external trend list') and immediately scopes it as 'discovery evidence, not a TrendsAGI measurement' with 'no volume or velocity'. That explicitly separates it from the measured-trend siblings such as list_trends and get_trend.

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 a concrete use case: 'catch a label that has not appeared in the measured trend table yet'. It does not name the alternative tool outright, but the measured-trend framing implies the boundary, and the matched_trend_id note tells the agent what to do when the label is already covered.

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