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

Goes well past the annotations by disclosing a full two-phase commit protocol: the first call is non-mutating and only validates, it returns a summary plus confirm_token, and unknown fields are rejected by name. That is precisely the behavioral context annotations cannot convey, and it does not contradict readOnlyHint=false or idempotentHint=false, since the write happens only on the confirmed second call.

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?

Four short sentences, front-loaded with purpose and permission before the procedural detail. Every sentence carries a distinct obligation (auth, call count, first-call semantics, human-in-the-loop step) with no restatement of the title or schema.

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 an 8-parameter mutation with a non-trivial confirmation flow and no output schema, the description covers the hard parts: auth scope, the two-call sequence, and the confirm gate. It leaves open how the three document-source modes interact and what the second call ultimately returns, which is a modest gap rather than a blocking one.

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 88%, so baseline would be 3, but the description adds real meaning: it tells the agent that confirm_token must be omitted on the first call and that the second call must repeat the identical arguments plus the token. It also explains the additionalProperties=false rejection behavior. It does not clarify whether file_id, content_html, and template_key are mutually exclusive, which is the one thing left to the schema.

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 ("Add a document to an offer"), which cleanly separates it from siblings like edit_document, remove_document, and convert_document. An agent knows immediately what class of operation this is 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?

Gives explicit operating conditions: requires `bookings:write`, must be called twice, and the first call must be followed by human confirmation before the second. It does not name alternative tools for adjacent goals (e.g., list_document_templates to find a template_key, convert_document to extract text), so there is no explicit exclusion guidance, but the when-and-how is clear.

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