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

With no annotations, the description carries the behavioral disclosure burden and does it well: it reveals relation defaults (epistemic §7), the opt-in engineering/all classes, the document special case (worked documents by citable id/title with live claims_count), and the hard exclusion of process records. It does not describe output format, ordering, or pagination, but the main behavioral traps are surfaced.

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 dense but front-loaded: core purpose first, then relation_class behavior, then the document special case, then exclusions and alternatives. Every sentence earns its place, and inline examples like '2605.05987 / arxiv:2605.05987' add practical value without 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?

For a 7-parameter search tool with no output schema, the description covers the important invocation traps: the relation_class default, the restricted meaning of kind=document, the process-record exclusion, and sibling routing. It does not specify return shape or pagination, but those are not required to select and call the tool correctly.

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 only 57%, so the description must add meaning for the less-documented parameters. It does: kind is explained with the document special case, relation_class is given a default and opt-in behavior, and query forms for documents are illustrated. limit remains unexplained, but the description targets the non-obvious parameters.

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 opens with a specific verb and resource: 'Keyword search the scientific graph (claim/relation/activity/metric/bundle).' It further distinguishes the document kind from other kinds and explicitly routes semantic search to methodist_search_semantic, so the tool's unique role is unmistakable even among many siblings.

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 gives explicit when-not guidance: a document not yet in the graph should use search/find_by_id, not this tool, and semantic search over claims belongs to methodist_search_semantic. It also states the relation_class default and the opt-in path for engineering edges, so an agent knows exactly how to choose behavior.

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