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

Annotations already declare readOnlyHint/idempotentHint, so those add nothing. The description contributes real behavioral context beyond them: matching is fuzzy over aliases across three languages, and the result is a canonical slug rather than a full record. It doesn't say how many matches come back or how ties are ranked, keeping it off 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?

Two sentences, no filler. The core action and language scope come first, and the motivating use case follows as supporting context.

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 two-parameter lookup with no output schema, the description covers purpose, input expectations, and the shape of the return (a slug). It omits what happens on multiple or zero matches, a minor but real gap for a fuzzy-search tool.

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 baseline is 3. The description adds meaningful semantics the schema doesn't: `query` is matched fuzzily against aliases, not exact names, so partial and transliterated inputs are acceptable. `lang` handling is left entirely to the 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?

States a specific verb and resource ('fuzzy-search markers by alias'), scopes it to EN/RU/HE, and implies the output ('canonical Mediora slug'), which separates it cleanly from explain_marker and list_markers.

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 concrete triggering condition: the caller has a lab-local name rather than a canonical slug, with examples in three scripts. It does not explicitly name an alternative tool or state when not to use it, so it falls short of the top band.

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