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

Goes well past the annotations: it explains that active=false pauses rather than deletes ('the Gambit and its history stay readable'), that active=true resumes, that a non-live or non-owned Gambit answers 404, the api:account requirement, and that the full Gambit is returned. This is meaningful disambiguation of the destructiveHint=true annotation.

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?

Front-loaded with purpose, and every sentence carries information despite being a dense single paragraph. It is on the long side and packs several distinct ideas (routing, semantics, error behavior, confirmation) into one block, which slightly hurts scannability.

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 still specifies the return ('the Gambit in full, as get_gambit does') and the app_url field, plus error behavior and mutation prerequisites. An agent has everything needed to call it correctly.

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 only 50%, but the description compensates by defining the meaning of every parameter: active toggles pause/resume, monitor_interval_minutes sets check frequency with its allowed values, and update_categories sets what is watched. It also constrains case_id to a UUID from list_gambits.

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+resource with scope: 'Change what Gambit watches for one of YOUR Gambits, or stop tracking it.' It names the related siblings (list_gambits for the case_id, get_gambit for the return shape), so an agent can distinguish it from neighbouring tools without opening a schema.

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?

Explicit routing: it names the trigger utterance ('stop tracking GOOGL'), tells the agent how to obtain the argument (find the case_id with list_gambits), and adds a procedural constraint ('Confirm with the user before stopping a Gambit'). Usage conditions and the required-argument rule ('Send at least one of the three') are all stated.

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