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

With no annotations, the description carries the full burden, and it does disclose two real behavioral limits: no live fetch and no guarantee that crawlers honour the output. That's meaningful, but it omits auth/permission needs, whether output is returned or written, and any side effects.

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?

Two short sentences, positive statement first, exclusions second. Every clause earns its place and nothing is padded.

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?

A generator tool with an undocumented array-of-rules parameter, no output schema, and no annotations needs far more: the expected rule object shape and return format are absent, leaving the agent unable to call it correctly.

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 0% and the parameters are non-trivial: 'rules' is an untyped array with no item shape, and 'sitemaps' is never mentioned in the description. The phrase 'rules you supply' adds no structural meaning, so the agent cannot construct a valid value from the description alone.

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 ('Generate a robots.txt') plus a scope caveat ('from rules you supply'), which likely distinguishes it from the crawler-oriented siblings like check_ai_crawlers. It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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 negative constraints ('Does NOT fetch the live robots.txt') imply the tool is for authoring rather than inspecting an existing file, which partially routes the agent away from check_ai_crawlers. There is no positive statement of when to prefer this over audits or validators, and no prerequisites.

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