stemlab_midi_models

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, but the description adds the crucial fact not in annotations: the call returns a retained background job rather than an inline result, and base effect flags are none while conditional inference/download effects live in danceflow_component. That is genuine added context. The telegraphic 'Base effect flags: none' sits in tension with readOnlyHint=false (a retained job is a state mutation), though it is explainable as being about the permissions block, so it is not a flat contradiction.

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, purpose front-loaded, with routing and effects guidance layered after. Nothing is padded. The fragments are jargon-heavy ('Base effect flags: none') and read as machine-generated, which costs some clarity, but the size is appropriate.

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, so return values need not be spelled out, and the async-job note is a useful extra. The gap is scope: an agent still cannot tell what 'capabilities' this returns for STEMLAB MIDI models, nor how this differs from the several sibling model/capability inspectors in the same namespace.

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?

The only real payload is an empty 'arguments' object, so there is nothing parameter-specific to document; baseline applies. The description never mentions the permission flags, but the schema already explains the write/network/download/training/inference/publication acknowledgements and states they are 'not independent authority'. The description does complement this by telling the agent which effect classes are irrelevant here (none at base).

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 verb is 'inspect' and the resource is 'StemLab runtime or registered analysis capabilities', which is a specific enough framing to act on. But the tool name promises 'midi_models' and the description never mentions MIDI or models, so the core resource is left ambiguous. It also does nothing to distinguish itself from nearby siblings like stemlab_models, stemlab_evidence_models, or stemlab_analysis_actions.

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?

There is real routing guidance: 'without starting inference' delimits the no-inference case, and the agent is told to poll danceflow_job_status and to check danceflow_component for conditional inference/download effects. However, there is no statement of when to prefer this over stemlab_models or stemlab_evidence_models, and no explicit when-not condition beyond the inference exclusion.

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