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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description goes further by disclosing the return contract ('{task_id} or not_found') and the failure mode for an unscoped ambiguous lookup, which is genuine behavioral context beyond the annotations.

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?

Two tight sentences with no wasted words and the core action front-loaded. The 'P-KEYS:' token is opaque jargon that costs a beat of clarity, and the rationale clause is dense, but overall it is efficient and well ordered.

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 no output schema, the description usefully supplies the return shape and the not_found/ambiguity outcomes, and annotations carry the safety semantics. For a 2-parameter tool this is nearly complete; only richer error detail would push it higher.

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 50% (external_key has no schema description), and the description compensates by characterizing external_key as a 'stable caller-provided' key. It explains request_id scoping in terms consistent with, though not much beyond, the schema. Appropriate value added given the coverage gap.

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 (resolve) and resource relationship (external_key -> task id), which is clearly distinct from list_tasks/update_task/verify_task siblings. The 'P-KEYS:' prefix and the 'automation lane never hardcodes a UUID' rationale add flavor but the definition never names or contrasts an alternative sibling explicitly, keeping it just below 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?

Gives clear conditional guidance for the key parameter: scope with request_id, or omit it for a global lookup that errors on cross-project ambiguity. It also implies the intended usage (avoiding churned UUIDs) but does not point to a sibling for the case where you don't yet have an external_key.

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