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

With readOnlyHint=true already covering safety, the description earns credit by disclosing search scope ('user's saved files'), matching criteria (name, tag, folder), and a return contract ('Returns matching names, types, folders, and IDs'). It aligns with readOnlyHint and openWorldHint=false, though it does not mention no-match behavior or result limits.

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?

Four sentences, each earning its place: purpose+scope, usage example, return contract, and a category tag. The most decision-relevant fact — 'metadata only — does NOT read file contents' — is front-loaded in the first sentence, and there is zero 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?

For a one-parameter, read-only tool with no output schema, the description covers search scope, input semantics, and return values, effectively substituting for the missing output schema. Minor gaps remain: no-match behavior and result limits are undisclosed, and the relationship to the sibling octopus_search is implicit rather than explicit.

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 coverage is 100%, so the baseline is 3. The description adds meaning by extending query targets beyond the schema's 'file names and tags' to include folders, and by signaling that natural-language references like 'my Q1 report' are valid query inputs.

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 opens with a specific verb-resource pair — 'Find the user's saved files by name, tag, or folder' — and immediately differentiates from content-search siblings by adding 'metadata only — does NOT read file contents.' Concrete examples like 'the invoice from this morning' make the tool's purpose vivid and 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?

'Use it to resolve a reference like ... to a real file' provides explicit when-to-use guidance with realistic examples. The clause 'does NOT read file contents' implies a when-not boundary, but no alternative tool (e.g., octopus_search or octopus_read) is named to route content-requiring intents.

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