find_similar

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

With no annotations, the description carries the behavioral burden and does well: it discloses that an id input reuses a cached vector and that the query node is excluded from its own results, and that free text is embedded fresh. It doesn't state that the operation is read-only or describe result shape, though an output schema exists to cover the latter.

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 tight sentences: identity first, parameter semantics second, routing advice last. Every clause earns its place and there is no padding.

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?

The output schema removes the need to describe return values, and the dual-mode input plus the self-exclusion behavior are covered. The only missing piece is how it relates to the search_nodes sibling, which an agent choosing between near-duplicate search and node search would want.

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 0%, so the description must compensate, and it does for the required parameter: text_or_id has two distinct modes (existing node id vs free text) with side effects spelled out for the id case. k is left entirely unexplained beyond its default of 5, which is the remaining gap.

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+resource and scope: 'Vector-only near-duplicate search -- the dedup primitive.' The qualifier 'vector-only' implicitly contrasts with keyword-based siblings, so an agent grasps what it does. It never names the obvious sibling (search_nodes), so sibling differentiation is inferred rather than stated.

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?

Gives a clear triggering scenario ('check is this already recorded') and explicitly steers away from an alternative method, grepping graph files, with a reason (paraphrase matching). It stops short of the 5 bar because it never mentions the sibling tool search_nodes, which is the most likely competing choice for the same intent.

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