Rank Short Form Candidates

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), lowering the bar. The description adds behavioral specifics beyond those annotations: 'Local-only plan' (no global/network computation), 'explainable' scoring, 'overlap suppression' of returned candidates, and the explicit promise that it never modifies Premiere state. Nothing contradicts the annotations; the extra context is genuinely additive.

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?

Two dense sentences with zero filler: the first front-loads the action verb and resource, then packs the scoring method; the second delivers three scope clarifications (local-only, not virality, no Premiere mutation) in one efficient clause. Every element earns its place, and the heuristic list, though long, is informative rather than repetitive.

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?

The tool is complex — 11 parameters, a nested word_timeline object with an ordered-words constraint, and an output schema — but the supporting structures are rich: the schema documents all parameters including the prerequisite transcript revision, and the annotations cover the safety profile. The description covers purpose, method, and scope exclusions, so nothing an agent needs to invoke it correctly is missing; only deeper composition guidance (how results feed downstream tools) is absent, which is beyond the description's burden given the output schema exists.

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 100% with defaults, ranges, and cross-tool references for every parameter (e.g., 'defaults to 30', 'added to the built-in lexicon', 'from local analysis'), so the schema carries the semantic burden. The description's heuristic list (hook, completeness, density, evidence peaks, keywords, duration fit, speaker consistency) maps conceptually to parameters like hook_words, keywords, min/max_seconds, and speaker_label, but it does not add per-parameter detail beyond what the schema already provides, so the baseline 3 applies.

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 description opens with a specific verb-resource pair — 'Rank long-video transcript windows as short-form clip candidates' — and names the exact method (explainable local heuristics) with concrete scoring dimensions. It explicitly states what the tool is not ('not a virality prediction' and 'never changes Premiere'), which clearly distinguishes it from the many plan_* and detect_* siblings. An agent can tell exactly what this tool produces and how it differs from adjacent 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 description provides clear context for when to use the tool: to score transcript windows as short-form candidates with local explainable signals, and it gives an explicit when-not in 'not a virality prediction'. The schema reinforces composition guidance by referencing sibling tools (detect_motion_peaks, detect_audio_transients) and the prerequisite get_clip_transcript_uxp revision, but the description itself does not name a sibling alternative to choose instead, so it stops short of a 5.

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