submit_edit

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

The description reinforces the annotations by stating the tool mutates Cosense, and adds useful behavior beyond them: the confirmation-before-retry rule and the need to verify with read_page. There is no contradiction with the annotations.

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?

Three terse sentences with the core action and mutation warning front-loaded. The retry guidance is concise and valuable with no wasted words.

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?

Given the annotations, output schema, and sibling context, the description covers the important invocation constraints: when to call, what it mutates, and how to handle ambiguity. It could explicitly name preview_edit as the source of preview_id, but the phrase 'produced the preview' covers this adequately.

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 description coverage is 0%, and the description does not explain project_url or preview_id. The names are somewhat self-explanatory, but for a destructive tool the description should at least clarify that preview_id comes from a prior preview step and what project_url refers to.

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 uses a specific verb and resource: 'Commit one inspected Cosense edit preview'. It clearly indicates this tool mutates Cosense, distinguishing it from read-oriented siblings like read_page and from preview-creation tools like preview_edit.

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 gives an explicit precondition: call it only for the same explicit user write request that produced the preview. It also states never to retry an ambiguous result before read_page confirms whether the change landed, which directly routes the agent to the correct fallback.

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