search_pages

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

With no annotations, the description carries the burden and does well: it discloses that only short snippets are returned, warns the snippet is a preview, and documents prefix matching plus the default and max limit. It does not mention cache staleness or whether refresh_cache is needed for fresh content.

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 behavior, then the actionable directive, then args. Slightly redundant, since 'Returns short snippets only' and 'The snippet is just a preview' make the same point, but nothing is filler.

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?

An output schema exists so return values need not be explained, and the description covers purpose, follow-up workflow, and both parameters. The only gap is cache-related context (e.g., when results may be stale and what refresh_cache does), which matters for a cached-index search tool.

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 0%, and the description fully compensates: 'query' is defined as space-separated keywords with a single-key-term-first and prefix-matching strategy, and 'limit' gets default 10 / max 20. Both parameters gain meaning found nowhere in the schema.

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 and resource ('Full-text search across all cached Confluence pages and external links'), including the searchable scope, so an agent can distinguish it from get_page, which it explicitly names as the follow-up step.

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?

Gives a clear workflow directive ('Always call get_page on relevant results to read the full content before answering questions'), which is exactly the context an agent needs. It does not, however, explain when to prefer search_pages over siblings like list_pages or refresh_cache.

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