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

The description discloses far more than the annotations: it never returns a near match, distinguishes statuses like `attested` from `not_in_corpus`, reports `date_mismatch`, returns stubs unless `include: ['text']` is passed, and distinguishes gazette citations from the tool's own URLs. This gives the agent a detailed behavioral model beyond readOnly/idempotent hints.

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 long, but nearly every sentence carries distinct operational guidance: accepted formats, result statuses, stub behavior, and date mismatch. It is front-loaded with the key instruction ('Call this BEFORE...'). A small amount of repetition around the text stub could be tightened, but the density is justified for a complex tool.

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?

There is no output schema, so the description carries the full burden of explaining return semantics. It covers all major result statuses, evidence fields like `normalised_from`/`normalised_to`, `fundstelle`, `text_truncated`, `date_mismatch`, and even warns against verifying quotations against stubs. Nothing essential for correct invocation appears missing.

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 the baseline is 3, but the description adds real value: it clarifies citations are taken 'verbatim' and 'in the form you already hold it,' and it explains the `include` behavior in depth, including that `'text'` returns full text rather than a 300-character stub. That goes beyond the schema's own parameter descriptions.

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: 'Ground a batch of German legal citations against the corpus.' It further narrows scope by listing accepted citation kinds and explicitly declaring 'Call this BEFORE stating any citation you did not read here,' which sets it apart from sibling search/retrieval tools.

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 gives an explicit trigger ('Call this BEFORE stating any citation you did not read here') and explains how to handle each outcome, e.g., 'attested is not a failure... you may state that the decision exists.' It does not name sibling tools or explicitly say when not to use it, but the usage context is clear and actionable.

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