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

Annotations already establish readOnly, idempotent, non-destructive, but the description adds meaningful behavior beyond them: the 100-byte ceiling, that words already in title/subtitle are skipped, how word value is computed, and — since no output schema exists — what the response contains (field, chosen words, words left out for space, metadata check result). Not fully exhaustive: overflow handling for must_include and locale effects are unmentioned, keeping it below a 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?

Three tight sentences, front-loaded with what the tool produces before explaining input and return shape; no filler. The final sentence is a long enumeration of return contents, which is useful but slightly dense to parse.

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?

With six parameters, no output schema, and a non-trivial packing algorithm, the description does the heavy lifting: it covers inputs, the scoring/selection rule, the 100-byte constraint, and the return payload. It leaves edge behavior (a must_include term that cannot fit, or how locale alters casing/width) unspecified, which is the only meaningful gap.

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 every parameter already carries its own documentation; the description merely restates that candidates are scored searches and that title/subtitle words are excluded. It adds no meaning the schema lacks for locale, app_name, or must_include, so the baseline 3 for a fully documented schema 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 names a specific verb and artifact ('Packs the most valuable single words into a valid 100-byte App Store keyword field') and explains the underlying model: Apple merges title/subtitle/keyword-field words, candidates are scored searches, and each word's value is the sum of the scores of searches it completes. That level of specificity separates it cleanly from upstream siblings like suggest_keywords and from get_competitor_report without naming them.

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?

'Input is scored searches and the planned title and subtitle' positions the tool as a downstream step after scoring keywords, and the skipping rule clarifies the relationship to the title/subtitle. It stops short of explicitly naming an alternative or stating when not to use it, so the guidance is clear context rather than full routing.

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