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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses account and OAuth-client scoping, that only a completed result can be delivered, and that retry.afterSeconds governs polling. That is substantial behavioral context the annotations cannot convey. It does not describe the full response shape (e.g. the job status field itself) despite there being no output 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?

Five short sentences, front-loaded with purpose then narrowing to scoping, polling discipline, and delivery/authorization rules. Every sentence constrains agent behavior; nothing is decorative.

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 single-parameter read tool with no output schema, the description covers the recovery scenario, polling cadence source, terminal conditions, and the authorization boundary for retries. An agent has everything needed to call it correctly and stop 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 description coverage is 0%, so the description must carry the parameter's meaning — and it does, specifying the value must be the 'original quoteId', i.e. the ID from the original request rather than a newly issued one. The UUID format constraint itself is handled by the schema's pattern, so nothing essential is missing.

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 opens with a specific verb and resource — 'Recover the existing Recast job by the original quoteId' — which cleanly separates it from prepare_recast, confirm_recast, and get_recast_quote. An agent can identify the read/recovery role of this tool 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?

It states the triggering condition precisely: 'after a disconnect, timeout or ambiguous confirmation', and adds a negative rule that a missing job, failure, or refund never authorizes a replacement. It stops short of naming the sibling to call instead when starting a new job (prepare_recast/confirm_recast), so the alternative is only implied.

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