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

Annotations already cover read-only, idempotent, non-destructive safety, so the bar is lower. The description still adds real behavioral value: it guarantees 'Returns ambiguous instead of guessing — never auto-pick candidates[0]' and scopes itself with 'Does not grade props,' which is exactly the kind of tie-breaking behavior an agent needs beyond the annotations.

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?

Four short sentences, each earning its place: purpose, usage routing, ambiguity behavior, and scope exclusion, with the core action front-loaded. No filler or repetition of the name.

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?

An output schema exists, so return formatting needn't be explained, and the description covers the key ambiguity-handling behavior for a resolver. It stops just short of describing the options semantics (strict/permissive/ingest modes), which would help an agent choose parameters for a fuzzy-matching tool.

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 67% with nested clue/option objects, so the schema carries most of the load. The description only mentions that sport/team/event clues exist, adding little detail on the clues object or the options (mode, max_candidates, min_confidence) beyond what the schema already documents. Baseline 3 is appropriate.

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 and resource ('Resolve messy sports player names') and the concrete outcome ('to a Lumify player_id'), plus the clue types it consumes. It also distinguishes itself from siblings (grade_slip, search_players/get_player) by framing the task as normalization rather than search or grading.

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?

'Prefer this before grade_slip when the name is a fragment, initial, or nickname' gives an explicit trigger and a named alternative. However, it doesn't address the other plausibly overlapping siblings (search_players, get_player, resolve_team), so the routing guidance is clear but not exhaustive.

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