stemlab_evidence_models

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description still adds material value beyond that: it discloses the asynchronous contract ("Returns a retained background job; poll danceflow_job_status") and scopes effects ("Base effect flags: none", conditional effects deferred to danceflow_component), which an agent cannot derive from 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?

Four short sentences, front-loaded with the purpose before the async and effect caveats; nothing is redundant. The telegraphic phrasing ("Base effect flags: none") is terse but each sentence carries distinct information.

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?

An output schema exists and the async polling path is documented, which covers the return side well. But for a tool whose required `arguments` object is empty and constrained, and which has near-identical siblings, the description omits the invocation shape and sibling differentiation needed to call it confidently.

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%: the permissions object has its own description, but the required `arguments` object is empty with additionalProperties=false and no explanation anywhere. The description never mentions either parameter, so an agent gets no help on what to put in `arguments` or which permission flags to acknowledge for this call.

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?

"Inspect StemLab runtime or registered analysis capabilities without starting inference" gives a specific verb (inspect) plus a bounded resource and an explicit scope limiter. The one weakness is that the resource is described abstractly as "runtime or registered analysis capabilities" rather than as models/evidence, so the link to the tool name and to the sibling stemlab_models is not made explicit.

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 implies when-not to use inference ("without starting inference") and routes to danceflow_component for conditional inference/download effects, which is real guidance. However, it never states when to choose this over the very similar stemlab_models, stemlab_doctor, or stemlab_analysis_actions siblings, leaving the primary selection decision to inference.

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