Graph Query

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

readOnlyHint=true already establishes this as a safe read, so the description's added value is in return behavior: it discloses that results are up to `limit` nodes plus connecting edges within `max_hops`, each carrying weight and source provenance. That is meaningful context beyond the annotation, though it says nothing about cost, pagination, or missing-entity behavior.

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?

Three sentences, zero filler: purpose and scope first, routing decision second, return shape third. Each sentence carries distinct, non-redundant information and the discriminating constraint is front-loaded.

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 parameters, no output schema, and a graph traversal that could easily be misused, the description is complete enough to call correctly: it covers purpose, routing, and return semantics. The remaining parameters (min_weight, current_only, entity_types, context_level, project_context) are left entirely to the schema, which is acceptable at 100% coverage but leaves the traversal-filtering story thin.

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 goes slightly further by explaining how `limit` and `max_hops` jointly shape the result (matching nodes plus their within-depth connecting edges) rather than restating field names, which helps an agent reason about traversal depth.

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?

Opens with a specific verb+resource ("Query the memory graph by canonical entity name") and immediately names the sibling it is not: graph_search. An agent can distinguish this tool from the other 23 graph_* tools without opening either 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?

Explicitly states the selection condition ("when you know the entity name or close-to-canonical form", with examples like "Steve") and routes the other case to the alternative tool ("for natural-language phrasing or synonyms ... prefer graph_search"). When-to-use and the alternative are both spelled out.

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