Prepare a contribution

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

The annotations declare readOnlyHint, idempotentHint and destructiveHint=false, and the description reinforces this in plain language ('It sends nothing'), which is corroboration rather than mere repetition. Beyond that it discloses the return contents (exact preview, problems to fix, payload, draft_id) even though no output schema exists, and adds a behavioural constraint on corrections (each find must occur exactly once in its section). That is material context an agent would otherwise have to discover by failure.

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 scope and the key 'sends nothing' property are front-loaded, and nearly every clause carries operational weight. It is a dense single block, though; the correction-specific and ask-the-person instructions could be separated into their own lines to be scannable, which keeps it from a 5.

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 14-parameter, heavily nested tool with no output schema, the description covers the workflow (prepare, show, confirm, then submit), the safety profile, and the returns. Some per-kind field requirements are left to the schema, which is acceptable given 93% coverage, but an agent still has to consult the schema for which fields pair with each kind.

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?

With 93% schema description coverage the schema already explains most parameters, so the baseline is a 3. The description adds genuine meaning on top: the exact-match-once invariant for the correction `find` edit, the requirement to source those words from get_entry, per-kind requirements (label change needs conditions and evidence), and the instruction to solicit credit and declared interests from the person. These are non-obvious semantics not present in the schema text.

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 gives a specific verb and resource ('Check a contribution ... and prepare it for submission') and enumerates the five contribution kinds a caller can prepare. It also distinguishes itself from the submit sibling with 'It sends nothing', so an agent can tell the two apart without opening any 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?

It states the ordering rule explicitly ('get their explicit agreement before calling submit_contribution'), names a prerequisite for corrections ('copy the exact current words from get_entry into find'), and gives an exclusion ('It sends nothing'). It also instructs the agent to ask the person for missing data rather than invent it, which is direct when-to-do-this guidance rather than inference.

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