commit_mapping_changes

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

With no annotations at all, the description carries the full burden and does meaningfully better than average: it discloses the auth source (BULLHORN_MCP_ACTOR), the permitted decision values, and the three possible outcome statuses including 'refused', which hints at a safety/consistency guard around diff_hash. It does not explain what triggers 'refused', whether the proposal is consumed or reusable after commit, or whether the operation is idempotent.

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?

Cleanly structured into a summary line, an Args block, and a Returns block, with the purpose front-loaded. The repeated 'returned by propose_mapping_changes' phrasing is slightly redundant, but nothing is padded.

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-param mutation tool with no annotations, it covers arguments, precondition, caller identity, and outcomes. An output schema exists so the Returns recap is optional rather than required; the remaining gap is the absence of failure/refusal conditions and post-commit state of the proposal.

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 0%, so the description must carry all parameter meaning and does: it documents all three required params, gives provenance for proposal_id and diff_hash, and supplies the effectively-enumerated 'approve'/'reject' domain for decision, which the schema omits entirely. This is close to full compensation for the coverage gap.

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 pair (approve/reject) applied to a specific resource (a stored proposal), and explicitly ties that proposal to the sibling tool propose_mapping_changes. An agent can distinguish this from propose_mapping_changes and other mapping tools without opening the 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?

The provenance of proposal_id and diff_hash ('returned by propose_mapping_changes') makes the ordering precondition clear: this tool is called after a proposal exists. There is no explicit statement of when NOT to call it (e.g. proposal already committed, hash stale), so it falls short of full when/when-not guidance.

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