aetre_author_preflight_benchmark

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. Yet it only says the tool 'calculates' metrics — it never discloses what the return value looks like, whether the optional api_key triggers external service calls or lifts rate limits, or whether this is a long-running/heavy computation. For an analysis tool with zero annotation coverage, this is a significant transparency gap.

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?

A single front-loaded sentence that leads with the primary purpose ('pre-submission diagnostic scorecard') before listing outputs. There is zero waste. It loses one point only because it packs several deliverables into a somewhat dense clause rather than breaking them out.

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?

This is a complex tool producing multiple outputs (novelty percentile, disagreement risk, prescriptive actions) with no output schema to fall back on, yet the description never states the return format. An agent cannot predict whether it receives percentages, a report, a score, or structured JSON. For a 4-parameter benchmark tool with no output schema, the description should disclose the deliverable 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 description coverage is 100%, so the baseline of 3 applies. The schema already documents all four parameters clearly (text, title, api_key, selection_boundary), including the tau default of 1.2. The description's mention of 'crowd novelty percentile' loosely maps to the selection_boundary concept but adds no parameter-level detail beyond what the schema supplies.

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 states a specific verb-context ('diagnostic scorecard for authors') and enumerates concrete outputs (crowd novelty percentile, reviewer disagreement risk, refinement actions), which distinguishes it from analytical siblings like triage_proposal or simulate_benchmark. It falls short of 5 because the tool's relationship to the 'aetre_preflight' family isn't fully pinned down, but the purpose is unambiguous.

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 'pre-submission diagnostic' framing implies a use-case context but provides no explicit when-to-use vs when-not-to guidance and names no alternatives. Among ~20 similar aetre siblings (triage_proposal, batch_triage, calibrate_scorer), an agent is left to infer that this is the one to run before submission, with no exclusions or routing cues.

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