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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the evidence payload (intent.score 0–100, tier thresholds hot ≥65/warm ≥35, signals with post excerpts, the judge's daily check), the precedence of the agent's decision over the judge, and the prompt-injection warning that public profile text is untrusted evidence.

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?

Front-loaded with the core action and the tool is dense with useful detail rather than filler. Sentences are long and heavily parenthetical, which slightly reduces scannability, but every clause carries information an agent needs.

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?

There is no output schema, and the description compensates well by describing exactly what each candidate carries (score, tier, signals, judge). Paging, filtering, untrusted-content handling, and non-actions are all covered; the only gaps are playId semantics and the phantom nextCursor/'reviewed' references.

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 only 20%, so the description carries the burden, and it does explain `after` (omit to get next unreviewed) and the `limit` range (1–200). However it introduces inconsistencies: it tells the agent to 'use nextCursor' though no such parameter exists, and references a 'reviewed' filter that is not in the enum (unreviewed/good_fit/not_a_good_fit/all). Real added meaning, but with defects that could mislead.

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 concrete verb+resource+scope: fetch 1–200 saved public profiles for batch-review Plays, returning review progress, Play revision and selected sequence. It is clearly distinguishable from review_x_play_candidates (which records the decision) and manage_x_play (which selects the sequence), both named explicitly.

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?

Explicit when-to-use and when-not: decide fit yourself when the customer gives chat rules, your review_x_play_candidates decision overrides the judge, omit `after` for the next unreviewed people, and 'This only reads; it does not fetch X, enroll or send.' It also routes to manage_x_play for sequence selection, so the agent knows the alternatives.

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