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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds valuable behavioral context: it retains an idempotency tombstone until expiry, does not reset quotas, and requires a bearer access header. This goes beyond the annotations and informs the agent of side effects and required authentication.

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 description is two sentences, front-loaded with the core purpose and followed by key behavioral details. Every sentence adds value: the first identifies the action, the second covers idempotency, quotas, and authentication. No filler or redundancy.

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?

The description covers the essential aspects for a single-parameter delete operation: what is deleted, side effects (tombstone, quotas), and required authentication. The output schema likely documents the response, and the tool's simplicity means little is missing. Minor gaps include error conditions (e.g., non-existent job_id) but these may be covered by the output schema.

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?

The schema documents job_id as a required string with a pattern, but provides no description, and the tool description does not elaborate on this parameter. With schema description coverage at 0%, the description should compensate, but it only vaguely implies that job_id identifies the result content. No additional semantics like naming conventions or the relationship to the owner are given.

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 clearly states the verb ('Delete') and the resource ('stored result content'), and it contrasts with sibling tools like get_catalog, get_job, and submit_* by indicating a deletion operation. It also adds specificity about idempotency and quota behavior, making the purpose unmistakable.

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?

The description does not explicitly state when to use this tool versus alternatives. It implies usage for deleting a job's result, but provides no exclusions or conditional guidance (e.g., 'use get_job to retrieve, delete_job to remove'). The authentication note ('Configure the owner's bearer access header') is a prerequisite, not a usage rule.

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