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

No annotations exist, so the description carries the full behavioral burden and mostly doesn't meet it. It never says whether re-adding a document with an existing title replaces or duplicates it, whether content is indexed immediately, whether size limits apply, or what owner_key authorizes.

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?

One front-loaded sentence with a clear verb, object, and a compact parenthetical of examples; nothing is wasted and the action comes first.

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?

For a 4-required-parameter mutation with no annotations, no output schema, and an undocumented credential parameter, the definition omits too much: prerequisites, duplicate/replace behavior, and confirmation of what the caller gets back are all missing.

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 50%, and the description maps to the 'title and full text' parameters, matching what the schema already documents for title and text. The required owner_key is never explained in either place, and 'site' semantics (identifier format, ownership) remain unaddressed.

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?

Specific verb+resource: 'Give a site's AI a document to answer visitors from,' with concrete document examples (menu, price list, rules, FAQ) that make the effect vivid. It does not distinguish itself from siblings like make_ai or change_site, so an agent must infer that this adds reference content rather than provisioning the AI.

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 clause 'to answer visitors from (a menu, price list, rules, FAQ)' implies the use case well: supplying grounding content. However, there is no explicit when-not guidance, no prerequisite stated (e.g., whether the site/AI must already exist via make_ai), and no mention of alternatives.

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