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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely new behavior: writes (INSERT/DELETE/LOAD/CLEAR) are refused, and results are capped — neither of which is visible in the 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?

Front-loads the verb and endpoint, then adds scope, prefix, and safety constraints in two tight follow-on sentences. The full prefix URI is verbose but earns its place since agents need it to build queries.

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, and the description covers result capping but not the shape of returned bindings. For a query tool with fully documented parameters and annotations carrying the safety profile, this is close to complete but leaves return format to inference.

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% and the schema itself documents both parameters well, so the baseline is 3. The description adds the `cdm:` prefix mapping, which is real construction guidance not stated in the schema's property 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?

States a specific verb (run your own SPARQL SELECT/ASK) and resource (Publications Office CELLAR endpoint), and explicitly carves out its niche as 'EU-document questions no purpose-built tool covers', which distinguishes it from siblings like cellar_search_works and cellar_work.

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 clear selection rule — use this when no purpose-built tool covers the question — and enumerates the kinds of questions it is for (citation graphs, amendment chains, EuroVoc traversal, cross-institution counts). It does not name the alternative tools explicitly, so routing is inferred rather than spelled out.

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