search_articles

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

Annotations already carry readOnlyHint and openWorldHint, covering the safety profile, so the bar is lower. The description adds genuinely useful behavior beyond that by stating it returns only 'titles, links and matching snippets' rather than full text, which sets expectations about output richness. No contradiction with 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?

Two sentences with zero filler; every clause earns its place. The front-loaded opening states both operating modes, and the subsequent clauses add distinct value: return format, then routing to get_article.

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 8 optional parameters and no output schema, the description compensates by disclosing the return contents and both operating modes, while the schema fully documents parameters and annotations cover the read-only safety profile. Minor gaps remain — no mention of pagination behavior and no differentiation from list_articles/search — but nothing essential to making a correct call is missing.

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 every parameter already documented (e.g., 'Page number for pagination,' 'Only articles in this category'), so the baseline of 3 applies. The description's 'search by keyword, or list articles in a category/section/label' phrasing reinforces the OR-relationship between query and the filter params, but adds little meaning beyond the schema's own note that query is optional when filters are given.

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-resource pair ('Search Help Center articles by keyword, or list the articles in a category, section or label') and discloses what it returns (titles, links, matching snippets). It explicitly distinguishes from get_article via a routing note, though it does not clarify how this differs from the sibling list_articles or the generic search tool.

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?

Provides an explicit when-not instruction: 'use get_article for an article's full text,' which routes the agent to the right alternative for fuller content. However, it gives no guidance on when to prefer list_articles or the generic search tool for the listing mode, leaving part of the sibling overlap unaddressed.

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