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

Annotations already declare readOnly, idempotent, non-destructive, openWorld. Beyond those, the description adds real behavioral context: the allowlist of official sources (with example domains) and the 30,000-character cap, which tells the agent output may be truncated and which inputs are rejected. It does not describe behavior on non-allowlisted URLs, leaving a small gap.

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?

Three sentences, front-loaded with what/how (fetch, clean, source constraints), then the cap, then the workflow pairing. No filler; every sentence carries actionable information.

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?

No output schema exists, but the description conveys the return shape ('cleaned full text') and its truncation limit, plus the allowlist and the URL-sourcing workflow. For a read-only tool with annotations covering safety, this is nearly complete; only edge-case behavior (invalid/non-allowlisted URL response) is unstated.

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 value by naming concrete allowlisted domains (ejustice.just.fgov.be, eur-lex.europa.eu) for the url parameter and restating the character cap tied to max_chars. This gives the agent more concrete grounding than the generic schema text alone.

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?

Specific verb phrase ('Fetch and clean the full text') plus a precise resource ('official Belgian or European legal document') and scope (HTML or PDF, allowlisted URL). It distinguishes itself from siblings by naming the lookups that supply the URL, so an agent can place it in the workflow without opening a schema.

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 a clear routing rule: use legal_lookup / eurlex_lookup to obtain the URL first. It implies the tool should not be called with arbitrary URLs via the allowlist constraint, but it never states explicit exclusions or failure behavior for non-allowlisted domains, so it stops short of a full when/when-not treatment.

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