Build citation-registry report shell

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

With no annotations, the description carries the full behavioral burden and does disclose the key side effect: the markdown is saved to data/reports/ in addition to being returned. It omits what happens on filename collisions, whether existing reports are overwritten, and any permission requirements, leaving meaningful gaps for a write-capable tool.

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 dense sentences with zero filler; the output contents are front-loaded and the return/persistence behavior is stated last where it belongs.

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 usefully states both the return value (markdown) and the storage location. For a two-parameter tool with fully documented schema this is nearly complete, though it could say what the saved artifact is named or how check_report consumes it.

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 description coverage is 100%, so the schema already documents both 'topic' and 'sources', including the 'previously scored with fetch_and_score' constraint that the description echoes. The description adds no new parameter-level detail, so the baseline 3 is appropriate.

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 (assemble) and resource (report shell) and enumerates the three sections it produces: claims stubs, numbered citation registry, scoring appendix. 'Shell from already-scored sources' implicitly separates it from plan_research and fetch_and_score, but no sibling is named explicitly.

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?

'From already-scored sources' implies the prerequisite that fetch_and_score must run first, which is genuine usage context. However, there is no explicit statement of when to call this versus check_report, or what to do if sources are unscored.

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