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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the bar is lower. The description adds real value beyond them by identifying the upstream source (HUDOC), disclosing the caching model ('live lookup with a short-lived cache, not a stored dataset') and enumerating what each result carries.

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 well-formed sentences, front-loaded with purpose and followed by the freshness caveat. The result-field list is dense but earns its place since there is no output schema; no filler text.

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?

With no output schema, the description compensates by naming the returned fields, and it explains data provenance and freshness. What is missing is any mention of pagination behavior for start/limit, which matters for a 100,000-offset result set.

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 80%, so the schema documents query, start, article and language already. The description adds only indirect signal – mentioning engaged articles and Ukrainian translations hints at the article and language filters – without stating syntax or accepted values beyond what the schema says. Baseline 3 applies.

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 (Search) and resource (ECHR case law via HUDOC) and adds a precise scope (cases against Ukraine) plus the record types covered (judgments, decisions, communicated cases). This distinguishes it cleanly from ua_echr__get_case and from the many other ua_*__search 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 scope statement ('cases against Ukraine') implies when this tool is appropriate, but there is no explicit instruction to use ua_echr__get_case once a case is identified, nor any note about when results will be empty or how to broaden a query. Usage is inferable rather than stated.

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