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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds behavioral context about sorting ('Sorted by level, then work done, then minutes to the first call'), pagination ('Up to limit results (default 25, at most 100)'), and empty-result behavior ('none match: an empty list'). That is useful, but it is couched in very dense prose and doesn't clarify rate limits, auth, or whether the search index is live.

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?

This is an extraordinarily long, run-on description - roughly 250+ words in a single paragraph with nested parentheticals. The core purpose (search tested products) and critical usage guidance are front-loaded only if the agent reads the first ten words; the rest is a stream of return-field explanations, filter restatements, and glossary definitions. It is not appropriately sized and forces the reader to parse dense prose to find invocation-relevant details.

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 carries the burden of explaining returns, and it does so thoroughly: level and its name, access, the five outcomes, part scores, wall_type, origin, and page URL. It also covers sorting, pagination, empty results, and routes to get_tool and list_categories. The main gap is that it never states when not to use it versus find_tools_for_task, a sibling that likely overlaps.

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 description coverage is 100%, so every parameter is already documented in the schema. The description restates filters and adds the min_level 0-5 meanings (0 Read-only through 5 Autonomous) and access enums, which is additive for a human but largely redundant with the schema. Per the rubric, 100% coverage sets a baseline of 3, and the description does not add syntax or format details beyond what the schema provides.

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+resource: 'Searches AgentDrives' tested products by name, domain or what they do'. It clearly distinguishes itself from get_tool (which returns one product's full result) and list_categories (which gives category ids). However, the opening sentence is buried under a 250-word run-on that mixes filtering, sorting, and output-field explanations, so an agent must dig to extract the core purpose.

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?

It names alternatives explicitly: get_tool returns one product's full result by a slug from here; list_categories gives the category ids. It implies this is the directory search and that get_tool is the drill-down. It does not explicitly say when NOT to use it (e.g. if you already have a slug) or when to prefer find_tools_for_task, which is a sibling that may overlap.

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