link_suggest

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

Beyond the readOnlyHint annotation, the description reveals the ranking logic: suggestions require at least two shared neighbours, exclude already-linked concepts, discount hub evidence, and fall back to title matching for unlinked concepts. That is genuinely useful behavioral context. It stops short of stating return shape or ordering, so not a 5.

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?

It is a single, front-loaded sentence with no filler. However, the telegraphic, semicolon-joined heuristic is dense enough that it takes a second read to parse, which slightly undercuts readability.

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 read-only tool with no output schema and no parameter documentation, the description carries the heuristic well but leaves two important gaps: what the caller receives (a ranked list of concept suggestions) and what 'limit' bounds. Minimum viable, but not complete.

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% and neither parameter is documented in the schema. The description never mentions the required 'id' (only the vague 'this one') or the optional 'limit', so an agent must guess what each parameter controls. The description does not compensate for the coverage 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?

The description states a concrete function: propose 'existing concepts this one probably should link to', which is a specific verb+resource for a link-recommendation tool. It implicitly separates itself from graph_neighbors (existing links) and concept_expand, but never names an alternative, so the differentiation is inferential rather than explicit.

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?

It describes the selection criteria ('at least two shared neighbours, not yet linked, hub evidence discounted; for an unlinked concept, title matches'), which implies when suggestions will be produced. However, it gives no explicit when-to-use-this-vs-alternatives instruction and no prerequisites, so usage is only implied.

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