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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, openWorldHint=true), the description discloses fund reservation, required write scope, external-lookup consent, the limited meaning of a title match, human-fallback behavior, and prompt-injection caution. This is rich behavioral context that materially changes how an agent should call and interpret the tool.

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?

It is dense but front-loaded with the action and auth requirement, and each sentence carries a distinct operational constraint. The paragraph style with multi-part clauses ('A title match establishes bibliographic identity, not semantic truth') is compact but sacrifices scannability, so it is not a perfect 5.

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?

Given the high complexity (nested constraints, discriminated acceptance, funds reservation) and no output schema, the description covers auth, retry/idempotency, cost, external lookup, human fallback, and the correct status/outcome workflow. It omits explicit error/response details and guidance for less central fields, but it provides enough for a competent agent to invoke the tool and continue the workflow.

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 only 11%, so the description must compensate, and it does for key parameters: 'explicit budget' maps to max_spend_cents, 'workflow and branch identifiers' maps to continuation, 'acceptance modes' maps to the discriminated oneOf, and idempotency_key recovery is called out. It does not annotate every parameter (e.g., target_reliability, traffic_class), but the most decision-critical fields are given semantic meaning.

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 names a concrete verb and resource: submit the shared /resolve envelope with an ME API key, and it states the outcome (durable pending/result state). It does not explicitly contrast itself with the closely named sibling me_resolve, and phrases like 'shared /resolve envelope' rely on internal vocabulary, so it stops short of a 5.

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 gives clear operational guidance: use requests:write, preserve the input and idempotency_key on recovery, poll me_resolution_status, and report downstream truth through me_resolution_outcome. However, it never tells the agent when to choose this tool over me_resolve or related resolution/verification tools, so the when-vs-alternatives dimension is only partially covered.

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