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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds meaningful behavioral detail: the anti-fab note that only candidates from the arg are matched (no implicit vocabulary expansion) and the explicit return format (candidates[].candidate, score, span). It also mentions the empty-candidate rejection, complementing the schema. No contradiction with annotations.

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 well-organized with bold labels (When to use, When NOT to use, Required args, Typical chain, Multi-call, Anti-Fab note). Every sentence carries essential information; there is no filler. The core purpose is front-loaded, and the structure makes scanning easy for an agent.

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?

Despite having no output schema, the description supplies the return format. It covers prerequisites (candidates non-empty), the anti-fab constraint, multi-call behavior, and the intended chain. For a tool with two required parameters and a nuanced matching rule, this is a complete operational guide.

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 100% (both text and candidates have descriptions). The description adds semantic clarity: it explains that the candidate list IS the vocabulary and must be non-empty, and it outlines the candidate structure ({name, synonyms?, coord?}). This goes beyond the schema's basic property descriptions, justifying a score above the baseline 3.

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 precise verb+resource statement: 'Match-Mention gegen Caller-supplied Kandidaten-Vokabular' (match mention against caller-supplied candidate vocabulary). It explicitly contrasts with specialized link_* tools by naming the alternative family, making the tool's unique role unmistakable.

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 provides explicit when-to-use (caller has custom vocabulary) and when-not-to-use (standard place/stop/time etc. go to specialized link_* tools). It also adds a typical chain, multi-call guidance, and a critical constraint (candidates must be non-empty), leaving no ambiguity about invocation context.

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