Which hooks and subjects are getting traction

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces that with 'Read-only'. Beyond that, the description adds significant behavioral context: it never sums metrics across channels, it suppresses verdicts below 5 posts, and it explains how posts without a recorded hook are counted. It also states it returns a `finding` or a `reason`. These details are not in the annotations and are crucial for correct interpretation of results. No contradiction exists.

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?

The description is longer than average, but every sentence earns its place. It front-loads the primary verb and purpose, then moves to a numbered list of exclusions, a presentation instruction, and a concluding note on read-only and credits. The structure is clear and purposeful; nothing is fluff. The length is justified by the tool's behavioral complexity, so it gets a 4 rather than a 5.

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 tool with no output schema, the description carefully explains what the output looks like (`finding` or `reason`) and when each appears. It covers aggregation scope, channel-scoping rules, confidence thresholds (5 posts), and data-exclusion semantics. Given the complexity of this analytic tool, the description is nearly exhaustive. An agent would know exactly what to expect and how to present results. No critical context 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 100% (both `axis` and `channel` are described). The description adds contextual meaning beyond the schema: it explains that grouping is by 'hook (default), subject, channel, media format or posting hour' (matching the enum) and clarifies that channel is meaningful because 'every comparison is within one channel'. This rationale is not in the schema and helps the agent understand why restricting by channel matters. It earns a 4 rather than a 3 because it adds interpretative value.

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?

The description states a specific verb ('Aggregate'), a resource ('this brand's published posts'), and a defined analytical goal ('which hooks and subjects work'), then enumerates the grouping axes. It clearly distinguishes itself from per-platform insight tools like meta_post_insights or x_post_metrics by framing it as a cross-channel aggregate. The purpose is unambiguous and specific, not a tautology.

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 description explicitly lists three behaviors the tool deliberately will NOT do, with reasons, and instructs the agent to 'repeat them rather than paper over them'. It also gives direct presentation guidance ('Present the `finding` verbatim if there is one, and the reason if there is not') and notes the tool is read-only and costs 0 credits. This is strong usage direction, even though it does not name sibling tools, because it tells the agent how to act on the tool's output and what boundaries not to cross.

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