Search memory

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description adds genuinely non-obvious behavior: word-splitting of the query, quoted-phrase handling, case-insensitive matching, ordering by number of matched terms, and the fact that returned relations may have their other endpoint outside the result set. That last point is the kind of surprise an agent needs warned about.

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?

Purpose is front-loaded in the first sentence, followed by mechanics and routing. Every sentence carries information, though the result-ordering paragraph is dense enough that it could be tightened slightly without loss.

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 an output schema covering the return shape and annotations covering the safety profile, the description supplies the remaining behavioral contract: matching rules, ranking, relation inclusion, blank-query behavior, and the sibling to use for exact-name lookup. Nothing an agent needs to invoke this correctly 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%, so every parameter (query, since, before, agent) is already documented in the schema, including the quoted-phrase syntax and the date formats. The description restates the query syntax and the filter intent but adds no format or default details beyond the schema, so baseline 3 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?

States a specific verb and resource plus the three fields searched (name, type, observation text), which pins down the semantics precisely. It also explicitly differentiates itself from open_nodes ('To fetch entities by exact name, see open_nodes') and references read_graph for the filter semantics, so an agent can route correctly without opening a schema.

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?

Names the alternative (open_nodes) with the condition that selects it, explains the filter parameters' scope ('narrow the search to matching entries, as in read_graph'), and states the degenerate case ('A blank query returns every entity'). When-to-use, when-not-to-use, and alternatives are all covered.

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