lbb_reviews_manage

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

Far beyond the annotations: it discloses that accepting a change or accepting/correcting a value commits facts or applies an ontology change that can remove types and relations, that approval flows through MCP form elicitation with approval_declined and approval_required outcomes, and that LBB_MCP_DESTRUCTIVE=allow bypasses the client question. It also names 409 review_answered and 409 review_stale and the idempotency-key retry contract, all consistent with destructiveHint=true.

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?

The first sentence is well front-loaded, but the body is a dense block that restates the approval flow twice ('the server reads the items and asks the person to approve first' and again 'The server asks the person to approve it through the client'), and mixes create, answer, comment and withdraw semantics without paragraphing. Every fact is defensible but the packaging makes it hard to scan.

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 24-parameter, five-action tool with nested objects and no output schema, the description covers actions, per-kind decisions, approval and error outcomes, scope and idempotency. It never indicates what a successful response contains beyond 'returns the item' / 'comes back unchanged', which is a real gap given the absence of an output schema, though the detail parameter partially signals shape.

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 96%, so the schema already documents most parameters and the baseline is 3. The description still adds real meaning the schema does not: which decision each kind accepts, that value/option/note are conditional on the decision, that 'the same key again updates it' for create, that an item has exactly one answer, and the 1-500 bound on answer_batch.

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 first sentence names five concrete verbs against one resource ('File, answer, comment on or withdraw review items'), mapping directly onto the action enum, and the resource is distinguishable from the read-only sibling lbb_reviews. The follow-up detail on kinds and decisions sharpens rather than restates the 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?

Strong internal routing: it states when to use each action, that an ontology change must go through lbb_configure action=suggest_ontology_change instead of create, and that test scope writes nothing. It never explicitly contrasts this tool with the sibling lbb_reviews (read) or lbb_commit for direct commits, so a small inference is left to the agent.

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