Verify Usage

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

Annotations already signal that the tool is not read-only and not idempotent; the description adds that testing happens 'in isolation,' which is useful but not detailed. It does not disclose whether code is actually executed, what side effects may occur, or whether resource limits apply.

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?

A single, front-loaded sentence delivers the core purpose with zero filler. It is concise at the cost of depth, but that depth is penalized in other dimensions.

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 7 parameters, 2 enums, and an output schema, a one-sentence description is insufficient to guide safe invocation. It omits the workflow (e.g., context_id from resolve_library appears only in the schema), the purpose of modes/profiles, and any caveats about executing snippets.

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 43%, with max_bytes, profile, snapshot_id, and test_intent left undocumented. The description adds no parameter-level meaning and therefore does not compensate for these gaps.

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 uses a specific verb ('Test') and a clear resource ('a proposed invocation or composition in isolation'). This distinguishes it from sibling tools like service_status, resolve_library, and inspect_symbol, which serve different purposes.

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 implies a pre-flight testing use case but does not explicitly state when to use verify_usage instead of siblings or when to avoid it. No exclusions or alternative conditions are provided.

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