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

Annotations only declare readOnly/non-destructive/openWorld=false; the description goes well beyond them by disclosing return contents, the overlapping-category caveat (sizes never sum to the catalog total), the semantic caveat that bands classify risk not quality and ignore company size, and the meaning of the last-rebuilt date. These are exactly the interpretive facts an agent needs and cannot get from the annotations.

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 the trigger and the return payload before the caveats and exclusions, and every clause carries information. It is on the long side for a two-parameter tool, but the density means little could be cut without losing routing or interpretation value.

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, so the description must describe the response itself, and it does so field by field. Combined with the risk-vs-quality caveat and the accurate sibling routing, an agent has everything needed to invoke this correctly and interpret the result.

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% with a documented enum and default, so the baseline is 3 and the schema already carries the parameter mechanics. The description adds genuine semantic framing for the `category` argument — that categories are the vendor's own classification, that slugs are accepted, and that tools belong to several categories at once — which materially affects how an agent should phrase the 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?

States a specific verb and resource — reporting the risk landscape of an AI tool category — and enumerates exactly what the answer contains (count, band distribution, decay rate, strongest/weakest named examples). It explicitly contrasts itself with siblings compare_tools, recommend_tools and deadpool_digest, so an agent can route without opening a 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?

Opens with a concrete trigger ("when the user asks what a whole category of AI tools looks like"), supplies two realistic example phrasings, and closes with an explicit three-item "Not for" list naming the correct alternative for each. When-to-use, when-not-to-use, and alternatives are all present.

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