verify_csdb

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the three verification steps being run (schema, BREX, references), that CSS-skipped steps report as "not-run" (per schema), the pagination model, and the file-writing side effect of reportPath with the reduced response. It does not state read-only safety explicitly or cost/latency expectations for large folders.

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 dense sentences with the what/scope front-loaded, then paging, then the reporting side effect — no filler. The "etc." after publication modules is the one piece of avoidable vagueness.

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, yet the description tells the agent what comes back (one status per object plus valid / XSD error / BREX violation / unresolved reference / unreadable totals), which is what an agent needs to decide whether to page or write a full report. Missing only the default-folder provenance note (S1000D_CSDB_DIR) and any guidance on result size.

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 baseline is 3. The description adds meaning for offset/limit and reportPath (response keeps only statuses), but its phrase "data modules by default; optionally publication modules etc." slightly conflicts with the schema's stated default of include=[dm, pm], which is a small source of ambiguity rather than added clarity.

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 (verify) and a specific resource scope (every CSDB object found in the given folders), and names the output shape (one VerificationStatus per object plus category totals). It implicitly distinguishes itself from verify_data_module / check_references by verifying a whole folder of objects, but never names those siblings to make the routing explicit.

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 concrete operational guidance (use offset/limit to page, pass reportPath to persist the full report), which is useful. But it never says when to use this versus validate_schema, verify_data_module, or check_references — an agent must infer the batch-vs-single and whole-object-vs-single-check distinction on its own.

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