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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds a genuinely non-obvious side effect: turning approve off sends an email to the person, which is exactly the kind of context annotations cannot carry. It does not describe the response shape or whether re-setting the same mode is a no-op.

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 sentences, no filler, with the mode definitions and the email side effect front-loaded before the read-tool pointer. The opening sentence is long and slightly tangled with nested clauses, but each clause carries distinct information.

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?

With only two required, fully documented parameters and no output schema needed, the definition covers purpose, mode semantics, a side effect, and the read counterpart. The only real gap is confirming behavior on already-claimed sites or failure cases, which is minor at this complexity.

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 100%, so the enum values are already documented; the description nonetheless re-frames them as workflows tied to mttr_propose, which clarifies when 'approve' actually bites. It also constrains the site parameter to 'one of the person's claimed sites', a precondition not present in the schema's 'domain such as example.com' note.

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 (set how changes are approved) and immediately defines the two modes with concrete workflow meaning: automatic deploys each change as you go, approve requires mttr_propose plus approval. An agent can distinguish this from mttr_propose, mttr_proposal, and mttr_proposals without opening any 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?

Explains what each mode means in practice and routes the agent to mttr_proposals({ site }) to read the current setting before/after changing it. It does not explicitly say when NOT to call this tool (e.g. that this is per-site and the site must already be claimed), but the conditioning on 'one of the person's claimed sites' implicitly scopes it.

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