research_save

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

With no annotations the description carries the full burden and does well: it discloses that writes go to CSV/JSONL, that partial updates retain other fields/rows, that original bytes are automatically backed up, that assigned IDs and field errors are returned, and that it 'never infers truth or closes requirements automatically'. Only permissions/auth and concurrency behavior are left unstated, so it falls just short of a 5.

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?

The core action is correctly front-loaded, but the body is a dense semicolon-chained block of seven sentences blending parameter guidance, safety notes, return behavior and a status-tool aside. Little is wasted, but the run-on structure makes it harder to scan than a bulleted or sectioned layout would.

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?

An output schema exists, so return values need not be documented, yet the description still adds useful write/read semantics, backup safety and ID-matching rules for a 6-parameter mutation tool with nested anyOf objects. Remaining gaps ('task' meaning, object field shapes, auth) keep it below a 5.

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 0%, so the description must compensate and it only partly does: it clarifies 'draft' (path + optional content + complete=true) and 'replace' (names complete collections, matched by URL/claim/summary) and gives matching semantics for omitted IDs. The required 'task' parameter is never explained, and the internal shape of the sources/claims/requirements objects is left to the caller.

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?

The opening sentence gives a specific verb+resource: 'Save/update source, claim and requirement objects by stable ID', plus the storage side effect (writes CSV/JSONL). It distinguishes itself from research_status by noting that status 'exposes activity', but it never names the check_draft/check_reviewer siblings it could be confused with.

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 for the main modes: use 'draft' with path/content/complete=true, omit content to register an existing file, and use 'replace' to repair complete collections from recovered rows. It does not, however, say when NOT to save or how this relates to research_check_draft/research_check_reviewer as alternatives.

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