gitflic_mr_approve

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

The annotations already flag destructiveHint=true, idempotentHint=false, and readOnlyHint=false; the description explains the reason for all three by disclosing the toggle semantics that make the call non-idempotent and destructive. That is real added context rather than restatement, though it says nothing about permission requirements, error conditions, or whether an approval can be withdrawn by other means.

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?

A single sentence with the primary action front-loaded and the surprising side effect placed in immediate parentheses. Every clause carries information; nothing is wasted or repeated from the schema.

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 three-parameter mutation with no output schema, the definition covers the core behavior but leaves gaps: the two required identifiers are unexplained, no return value is hinted at, and there is no mention of permissions or of the error state when approval is disallowed. Adequate to call safely in the happy path, but not complete.

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 only 33%: 'raw' is documented in the schema, but 'project' and 'id' carry no descriptions, and the description does not tell the agent that 'id' is a merge request identifier or what form 'project' takes (path, slug, or numeric id). With low coverage the description was expected to compensate, and it does not.

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 plus resource ('Toggle approve on a merge request') and adds the counterintuitive effect in parentheses, so the agent knows exactly what state change occurs. It stops short of naming a sibling such as gitflic_mr_cancel or gitflic_mr_merge as the alternative for a different outcome, so the differentiation is implicit rather than explicit.

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 parenthetical 'calling twice removes the approval' is a genuine usage rule that tells the agent how the tool behaves on repeat invocation, which is more than most one-liners offer. However, there is no statement of prerequisites (permissions, whether self-approval is allowed), no mention of when to prefer gitflic_mr_view to check current approval state, and no guidance on what to do instead when the MR cannot be approved.

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