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

Annotations only flag write/idempotent/non-destructive; the description adds substantial context beyond them: required scope agent.inbox.read, agent-scoped bearer key requirement, that member/facility keys cannot impersonate an agent, idempotent replay semantics, and a deprecation timeline. This is exactly the extra behavioral detail annotations cannot carry.

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?

The deprecation notice is correctly front-loaded, but the body is a dense run-on of eight clauses, including opaque context such as 'rollout switches, current member approval, assignment, credential environment and SQL authorization are shared with REST' that does little to help tool selection. Information-dense but not tight.

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 an output schema present, the description need not explain return values, and it covers everything else an agent needs: auth/scope requirements, key-scoping rules, idempotency behavior, deprecation status, and the negative space of what the fixture does not do.

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 100%, and both parameters (scenario enum, idempotency_key pattern/length) are fully documented in the schema. The description restates the replay-key reuse rule but adds no syntax or format meaning beyond the schema, so the baseline 3 applies.

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 ('seed') and resource (an isolated provider-free two_page_letter or needs_review fixture) via a named endpoint /v1/agent-inbox/sandbox/seed. It also distinguishes itself from siblings by declaring that these fixtures test reads/reports, not handling, and that no real mail/model call/email/facility task is involved.

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 clear conditions: sandbox agent key only, deprecated with no successor but still served until the alias window closes, and an explicit 'never substitute another key or mail API after denial' exclusion. It does not name which sibling tool to use for the handling scenarios it disclaims, so it stops short of full alternative routing.

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