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

Annotations only declare readOnly/no-destructive; the description goes well beyond by disclosing cost and quota tiers, what the Lab's reply_sample is bounded to, that limits on what a public-API sample can prove are declared, and that it returns `result_url`. That is exactly the behavioral context an agent needs before spending a paid call.

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?

One dense paragraph, front-loaded with the verb and output shape, then mechanics, then pricing. Nearly every clause earns its place, though the parenthetical engagement-unit arithmetic ('reply 13.5 · quote 1.5 · repost 1.0 · like 0.5') is closer to marketing detail than invocation guidance.

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 2-param read tool with an output schema and readOnly annotations, the description covers modes, cost, quota, sampling limits, and the returned link. Only edge behavior (unknown handle, exhausted quota response) is left unstated.

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%, so the baseline is 3, but the description adds real meaning: `deep` is scoped to the Lab, returns a bounded reply_sample, and runs on its own daily lane (implying separate quota), while `handle` accepts an X handle with or without the @.

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: 'give it any X @handle and get an organic-ness audit', then names the concrete artifacts (0–100 score, ORGANIC/MIXED/SMOKE verdict, anchor in engagement units). No sibling in the list does anything comparable, so the agent can route here unambiguously.

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?

Explains the two modes clearly — default audit vs `deep: true` which adds the reply sample for quality judgement — and states the quota ('one free audit a day', then $0.02 in packs of 50, signed-out returns the price). It does not name a when-not-to-use case or point at any alternative tool, which keeps it below a 5.

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