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

Annotations are all false and carry no information, so the description carries the full burden — and it delivers. It discloses that submissions are stored per-user, visible only to platform admins, return an id + acknowledgement, cannot be read back, and should include machine context. This is rich behavioral context beyond the bare mutation implied by the false readOnlyHint.

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 long but dense — every clause earns its place: purpose, accepted feedback types, exclusions with alternatives, trigger timing, storage/visibility, response shape, and context instructions. It is front-loaded with the core purpose before the exclusions. Slightly heavy but all information is load-bearing for correct use.

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?

Complete for a 5-parameter feedback tool with no output schema and nested objects. It covers what to report, what not to report, when to call it, where the data goes, what the response looks like (id + acknowledgement), and how to fill the nested context object. The only small gap is that it does not spell out the category/severity enum semantics, but those are self-describing.

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 very low at 20%, so the description should compensate. It does add meaning for the nested context object ('Include machine context (tool name, session id, model)'), which is genuinely useful. However, it adds nothing for title, body, category, or severity beyond what the schema/enums already provide. The context guidance is valuable but the other four parameters are left to the schema, so compensation is only partial.

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?

States a specific verb and resource ('Report feedback about the META COUNCIL PLATFORM itself') and enumerates the exact kinds of feedback accepted (performance failure, missing capability, bug, UX/docs gap). It also names the sibling business tools it is not (create_deal, create_invoice), so an agent can distinguish it from the ~100 business operations without opening the schema.

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?

Provides both explicit positive trigger ('Use it the moment a tool result, council run, or workflow falls short') and explicit exclusions with named alternatives ('do NOT use this for anything about your own business... use the relevant business tool for that instead'). This is the strongest form of usage guidance — when-to and when-not-to with concrete routing.

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