Compute Sample

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description's 'compute' aligns with a non-read action. However, the description adds no extra behavioral details—such as what a 'recognition sample' entails, whether it creates persistent data, or any side effects 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?

The description is a single sentence with no waste, but it is too brief to be optimally helpful. For a tool with only two parameters, it could include a bit more context about what 'compute a recognition sample' produces or requires without becoming verbose.

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 is minimal: no output schema exists, and the description fails to explain what a recognition sample is, what the tool returns, or any side effects. Given the openWorldHint annotation, the tool may have additional undocumented behavior, leaving the agent underinformed.

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 100%, with basic descriptions for collId ('Collection ID') and docId ('Document ID'). The description does not add any additional meaning or context about these parameters, so it provides no value beyond the schema. Baseline 3 is appropriate.

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 'compute' and the resource 'recognition sample' for a document in a collection, which is specific and actionable. However, it does not differentiate from sibling tools like transkribus_recog_compute_error_rate or transkribus_recog_run_htr_citlab, all of which involve computing something recognition-related.

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?

No guidance on when to use this tool versus alternatives. The sibling list includes many recog_* tools, but the description gives no context on scenarios, prerequisites, or why a user would choose 'compute sample' over 'compute error rate' or 'run HTR'.

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