graph_review_candidates

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

With no annotations, the description carries the full burden and does much of it: it discloses that 'accept' merges the pair, that 'reject' permanently excludes it from future suggestions (an irreversible side effect), and that nothing auto-merges. The trailing '[passive] Reads the local graph database only' tag sits awkwardly against the merge-write behavior of 'decide', and permissions/auth requirements and pagination are not covered, keeping it below 5.

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?

Purpose is front-loaded in the first sentence, followed by a tight action-by-action breakdown and a critical constraint sentence. It is dense but every sentence adds a fact an agent needs, with no filler.

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 10-parameter tool with no output schema and no annotations, the description covers actions, filters, verdict semantics and the no-auto-merge constraint well. Minor gaps remain: return shape is only sketched for 'list', and there is no mention of permissions, pagination, or the ambiguous '[passive]' classification.

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 already 80%, so the baseline is 3; the description adds real meaning on top by mapping filters (schema, score range, dataset) to the 'list' action and mapping entity_id/canonical_id/decision/reviewer_id to the 'decide' action. It also explains that decision='accept' means merge and 'reject' means permanent exclusion, which the bare enum values do not convey.

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 resource and role: a 'human review queue for suggested same_as entity matches' produced by graph-dedup. This clearly distinguishes it from the sibling search_* tools and from graph_export/graph_neighbors, so an agent can identify it 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 description splits the tool by action and gives the condition for each: action='list' to browse pending candidates with filters, action='decide' to record a verdict. It also states the key selection fact that only this action can write judgement='positive'. It stops short of naming sibling alternatives to avoid (e.g. graph_neighbors for pure exploration), so it is strong but not fully exhaustive.

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