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

Annotations declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral detail beyond that: it defines the full status field contract ({status:"ok", data, fetchedAt}, not_applicable, timeout, error), clarifies that a missing robots.txt is treated as data rather than an error, and mentions the one-fetch/10s timeout. This gives the agent precise knowledge of what to expect in responses, going well beyond the annotation flags.

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 well-structured and front-loaded with the core purpose, then explains edge-case behavior and output format. Every sentence contributes unique value: the crawler list, the 'missing file is data' nuance, the timeout, and the status enum. It is slightly long but not verbose; the detail is justified given the complexity of the output contract.

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?

Given the tool's complexity (multiple crawlers, conditional statuses, edge cases) and the absence of an output schema, the description fully specifies the return structure and how to interpret each status. It also clarifies the semantics of 'not_applicable' versus 'error'. An agent has all necessary information to call the tool and handle results 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 100% for the single parameter 'domain', which is already fully documented in the schema (including rejections of IP addresses, ports, paths, and protocol prefixes). The description adds no further parameter-specific guidance beyond what the schema already provides, so the baseline of 3 applies.

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 ('Report') and resource ('domain's robots.txt') and enumerates the exact crawlers covered (GPTBot, ClaudeBot, Google-Extended, etc.). It clearly distinguishes itself from siblings like dossier_llms_txt and dossier_web_surface by focusing on AI crawler policy, so an agent can select it without opening the 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?

The description explicitly says 'Use to answer whether a site lets AI models train on or retrieve its content,' giving clear context for when to invoke it. It also explains the behavior for missing robots.txt ('a missing robots.txt is data, not an error'), which indirectly sets expectations. It does not name alternative tools for comparison, but the use case is specific enough that siblings like dossier_llms_txt are obviously different. Lacks explicit 'when-not-to-use' but remains clear.

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