fixEdits

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the key behavioral fact that the tool computes edits but does not write, which is critical for an agent to avoid unintended side effects. It could add more detail about the exact shape of the returned edits, but the core non-mutating behavior is clearly disclosed.

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?

Two sentences with no filler. The first sentence states the purpose and output; the second sentence states the critical non-write behavior and routes to the apply tools. Every word earns its place.

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 read-only computation tool with two parameters and no output schema, the description covers the essential context: input source, input proposal, output type, and the fact that it doesn't write. It doesn't describe the exact return structure, but the description's mention of 'ranges and replacement text' gives the agent enough to know what to expect. The sibling list includes patchObjectSource and editObject, which the description correctly names as the apply step.

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 50%: the 'proposal' parameter is described in the schema, but 'source' is not. The description adds meaning by explaining that 'proposal' comes from fixProposals and that the tool produces ranges and replacement text, which clarifies what the parameters are for. It doesn't fully describe the 'source' parameter, but the context of 'ranges' implies source text, so the gap is minor.

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 states a specific verb ('Turn'), a specific resource ('one proposal from fixProposals'), and the concrete output ('ranges and replacement text'). It also explicitly distinguishes itself from write tools by naming patchObjectSource and editObject as the apply step. This is a clear, non-tautological definition that an agent can act on.

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 explicitly says when to use this tool: to convert a fixProposals proposal into concrete edits. It also says what NOT to do: it does NOT write, and tells the agent to apply the result with patchObjectSource or editObject. This is explicit when/when-not guidance with named alternatives.

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