feedback_start

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the mutation and open-world profile is known. The description adds real value beyond them: it says the chain and its check options are persisted 'in files of its own', that the return is a feedback-v1 with at most one bounded action per finding, and that verifying is only 'advice' relative to state.task. It stops short of saying where those files live or how the chain terminates.

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?

Roughly 70 words with the action front-loaded in the first clause, and every sentence carries information rather than filler. The multipurpose phrasing ('buddie runs the check itself, keeps the chain and its check options in files of its own') is packed tight and takes a second read, which costs some clarity but no length.

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?

This is a complex, high-parameter, stateful workflow tool with no output schema, so the description must carry the return-value burden. It gestures at the feedback-v1 shape ('at most one bounded action per finding') but never explains what a finding or an action looks like, and it leaves the boundary with verify_report unstated. Adequate orientation, insufficient for a 14-parameter chain-starter.

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 100% across all 14 parameters, including enums and defaults for profile, checks, modules and numbers, so the schema does the heavy lifting and a baseline 3 applies. The description contributes one genuinely extra semantic link, tying the requirements parameter to what counts as a 'finished task' (state.task). The remaining 13 parameters, including fetch, repos, store, access and iteration_limit, get no added meaning in prose.

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+resource combination: 'Check a report and open a verification feedback chain'. It also pre-names the follow-up sibling (feedback_resolve), so the agent knows this is the entry point of a two-step flow. What it does not clarify is how 'Check a report' differs from the sibling verify_report, which reads as an overlapping purpose.

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?

The description gives downstream guidance ('correct only what an action names and call feedback_resolve') and a completion caveat ('a verified report is not a finished task unless the requirements you state are met'), but it never states when this tool should be chosen over verify_report or feedback_accept. The usage path is implied rather than spelled out.

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