save_run

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

Annotations already indicate this is not read-only and not idempotent; the description adds useful behavioral context by specifying that data is persisted to a local runs.db and that saving is user-initiated. It does not explain overwrite, duplication, or error behavior, but it goes 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?

A single compact sentence that front-loads the critical guardrail ('only when the user explicitly requests saving') before stating the action and target. There is no filler or repetition.

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?

Purpose and trigger are clear, but the only parameter is an opaque free-form object with additionalProperties: true and zero description. An agent would not know how to construct the payload. The presence of an output schema reduces the need to describe return values, but payload construction is an essential gap.

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 0%, so the description must compensate, but it does not explain the payload structure. Saying 'write a consultation' only implies the payload contains consultation data; it leaves the actual shape, required fields, and serialization format undocumented.

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 states the exact operation: writing a consultation to local runs.db, and adds a strong condition ('only when the user explicitly requests saving'). This clearly separates save_run from siblings like get_run, delete_run, and the various calculation tools.

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 explicit when-to-use guidance by requiring an explicit user save request, which also implies the tool should not be called automatically. It does not name alternative tools or describe when to prefer them, so it falls just short of the top score.

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