cc_presence

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the default crawl selection behavior and, importantly, the interpretive caveat that zero pages does not imply site absence. However, it does not describe the output format or potential edge cases (e.g., invalid domains), but the presence of an output schema mitigates the need for return details. Overall, it provides meaningful behavioral context beyond the schema.

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 extremely concise: two sentences, each earning its place. The first states the core function and purpose, the second provides essential caveats and a pointer to an alternative tool. No redundant information, ideal structure for an AI agent to quickly grasp.

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 simplicity (2 parameters, one optional), the presence of an output schema, and the no-annotation context, the description covers all essential aspects: what it does, default parameter behavior, and a critical interpretive caveat. It is complete for an agent to invoke correctly without additional documentation. The pointer to cc_dynamics also covers follow-up scenarios.

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?

The schema has 0% description coverage, so the description must compensate. It explicitly explains the 'crawl' parameter's default behavior ('crawl не указан — берётся свежий'), adding value beyond the schema's bare type/null default. The 'domain' parameter is not elaborated, but its purpose is implicitly clear from the tool name and description. This partial compensation justifies a score above baseline.

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 clearly states the tool's function: 'Сколько страниц домена попало в кравл' (how many pages of a domain are in the crawl), with a specific verb and resource. It also frames the purpose as checking site presence in LLM training data, which distinguishes it from siblings like cc_urls or cc_sections. The reference to cc_dynamics for further checks further differentiates its role.

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 provides explicit usage guidance: it explains the default behavior when the 'crawl' parameter is omitted ('crawl не указан — берётся свежий') and gives a clear alternative: if the result is zero, it advises checking via cc_dynamics because coverage fluctuates. This tells the user when to use this tool and when to switch to another, which is exactly what this dimension requires.

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