marm_concept_recall

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

No annotations are provided, so the description bears full responsibility. It discloses that returns are empty lists (not errors) when the build hasn't run or no matching code symbols exist, which is a key behavioral insight. It does not mention side effects or idempotency, but the read-only nature is implied and the emptiness behavior is well-covered.

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?

The description is well-structured with a clear opening sentence and bullet-like parameter explanations. It effectively front-loads the purpose. While it is somewhat lengthy (especially the parameter section), every sentence adds value, and the use of emoji and formatting aids readability without being wasteful.

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 tool with 6 parameters, no output schema, and no annotations, the description covers the overall purpose, parameter semantics, and key behavior (empty lists). It lists the return fields (entities, related_entities, linked_code) but does not detail their structure or pagination. Overall, it provides sufficient context for an agent to use the tool correctly, though additional info on output format would push it to 5.

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%, so the description must explain all parameters. It does so thoroughly: provides context for query (bare name vs traversal), clarifies session_name and project scoping, explains limit range and default, depth meaning, direction enum, and the distinct node behavior for projects. This adds significant value beyond the bare 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?

The description clearly states it searches the concept graph for entities, relationships, and linked code, with a specific verb 'search' and resource 'concept graph'. It distinguishes from siblings like marm_code_lookup by emphasizing graph traversal, but does not explicitly differentiate from marm_smart_recall or marm_graph_impact. The 'retrieves' purpose is well-defined.

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 description provides context on query phrasing ('bare concept name' vs 'related to X') and handles the case where build hasn't run. However, it does not specify when to use this tool over siblings like marm_graph_trace or marm_smart_recall, nor does it offer when-not-to-use guidance.

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