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

The description goes well beyond the annotations by disclosing the required `bookings:write` scope, the two-call dry-run pattern, the fact that the first call mutates nothing, and that unknown fields are rejected by name. That is exactly the kind of context the readOnly/destructive/idempotent hints cannot convey. It stops short of describing what state the extension ask is left in or what happens if the second call is never made.

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?

Three short sentences, purpose front-loaded, then permission, then the call sequence in order. The parenthetical about rejected fields is slightly dense but earns its place by explaining error behavior. Little waste overall.

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 destructive two-phase mutation with no output schema and partial parameter documentation, the description covers the essential mechanics: permissions, the confirm-token handshake, and human-in-the-loop confirmation. Gaps remain around the relationship between proposal_id and extension_id and any post-cancellation state, but the core is sufficient to invoke 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 coverage is only 33%, so the description must carry more weight; it does explain confirm_token's role fully ('the same arguments plus confirm_token'). It says nothing about proposal_id or extension_id, leaving their distinction (proposal vs. the specific extension) undocumented in both schema and description.

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 action on a specific resource ('take back an extension ask') and adds a scope qualifier ('before paying') that separates it from decline_extension or accept_extension. It does not name those siblings explicitly, so the agent must infer the distinction, but the operation itself is unambiguous.

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?

Usage is implied through the two-call flow and the precondition 'before paying', and the instruction to show the summary to the person is a concrete usage rule. However, no sibling is named as an alternative or exclusion — an agent choosing between cancel_extension, decline_extension, and request_extension gets no explicit routing guidance.

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