FleetQ

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions lifecycle actions (pause, resume, kill, valid_transitions) implying statefulness, but fails to disclose side effects (e.g., is kill reversible?), permission requirements, return value structure, or rate limits for the cost action.

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 a single dense sentence with parenthetical parameter lists. While relatively compact, it lacks structural formatting that would improve scannability (e.g., line breaks or bullet points for 13 distinct actions).

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 the tool's complexity (14 parameters, 13 distinct actions, no output schema, no annotations), the description is insufficient. It fails to explain return values, error conditions, or the relationship between experiments and workflows. The schema incorrectly marks all parameters as required for all actions; the description partially mitigates this by showing action-specific parameter usage, but this is not enough.

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 100%, establishing a baseline of 3. The description adds value by mapping actions to their specific parameters (e.g., create uses name/hypothesis), though it contains minor terminology mismatches (describing 'name' and 'hypothesis' while schema uses 'title' and 'thesis') and references parameters not present in the schema (workflow_id).

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 tool manages 'experiments (pipeline runs)' which defines the resource, but uses the vague verb 'Manage'. It lists specific actions (list, get, create, etc.) which helps clarify capabilities, but does not explicitly distinguish this from sibling tools like workflow_manage or crew_manage.

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 lists available actions and their associated parameters, but provides no guidance on when to use this tool versus alternatives, nor when to choose specific actions over others (e.g., when to use retry vs retry_from_step). No prerequisites or exclusion criteria are mentioned.

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