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

Annotations already declare this as non-destructive, idempotent, but read-write. The description adds meaningful context beyond that: the mapping is learned when several accounts observe the same thing on one firmware, and get_trust can later show learned mappings and differences from the driver. It does not mention permission or rate-limit constraints, but the crowd-learning behavior is valuable.

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 purpose is front-loaded and every clause carries information. The two sentences are dense but structured with parentheticals and em dashes; a slightly tighter phrasing could improve readability, but it is not padded.

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?

For a complex write/reporting tool with no output schema, the description covers the workflow, data sources, crowd-learning behavior, and where to inspect results via get_trust. It omits what the immediate response looks like, but the essential call context is present.

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 45%, so the description must compensate. It explains the key semantic groups: address (from list_routes) or label, the CC/NRPN/note message type, firmware, and identity_hex. However, it does not clarify channel or the distinction between NRPN MSB/LSB, leaving notable gaps for an 11-parameter tool.

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 opens with a specific verb and resource: 'Teach the catalogue which MIDI message a control really sends'. It distinguishes this tool from siblings relay_listen, list_routes and get_trust by clearly assigning each a different step in the workflow.

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 says when to use this tool ('after the user moved one control on the device'), directs where to get the OSC address (list_routes) and offers a fallback (panel label for controls the driver lacks). It references alternatives without explicitly stating when not to call it, so a 4 rather than a 5.

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