Retrieve Context

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

No annotations exist, so the description carries the full burden, but it does disclose real behavioral detail: results are organized into MUST_READ, DANGER, MAY_CHANGE and MUST_TEST sections and read-only intent. It omits any statement about permissions, cost, or mutation (none expected), which is acceptable given the retrieval nature. Value is added, but the output semantics come largely from the output schema.

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 dense, front-loaded sentences that waste no words and put the core purpose first, followed by result-interpretation guidance. The dense jargon (FTS5, PageRank, MUST_READ) is compact but not cryptic in context.

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 four-parameter tool with an output schema, describing return values is unnecessary, and the description does outline the semantic sections of the result. It is still incomplete on parameters and on how the result should drive subsequent actions beyond 'consider a change done', which is vague.

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% across all four parameters (query, top_k, vault, seed_k) and the description explains none of them. 'Natural-language description of a task' weakly implies the query's form, and 'FTS5-seeded, PageRank-expanded' hints at the seed_k/top_k tradeoff, but no parameter is actually defined, leaving the schema to carry undocumented fields.

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 purpose: graph-expanded context retrieval seeded by full-text search for a natural-language task, and frames itself as 'the main entry point'. The FTS5/PageRank mechanism distinguishes it conceptually from siblings like search_vault and search_nodes, though it never names or contrasts those alternatives directly.

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?

'The main entry point' implies this is the default starting tool for a task, which is genuine usage guidance. However, it gives no explicit when-not conditions and does not mention sibling retrieval tools (search_vault, search_nodes, neighbors) that an agent might confuse it with.

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