project_settings

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the risk profile is carried by structured data. The description adds useful context — the settings live in med-lit.settings.json, there are many settings beyond the listed ones ('and more'), and changes should be researcher-driven — but it never says whether supplied changes are merged with or overwrite existing settings, which is the key unknown for a destructive write.

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-loaded with the action, followed by the setting inventory, and closed with the caveat — a sensible order with little waste. The trailing 'and more' is slightly vague but honestly signals the list is non-exhaustive.

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?

With an output schema present, return values need no explanation, and both parameters are fully documented, so the description only needs to characterize the settings surface and mutation caution — which it does. The one gap is merge-vs-overwrite semantics on the write path, which matters given destructiveHint=true.

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 earns extra by naming concrete setting keys (research mode values basic/full/deep, max_screened, search.years, fetch.limit) that a free-form dotted-key object cannot express on its own. It effectively supplies the vocabulary an agent needs to construct a valid `changes` payload.

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 pair and resource ('Show or change a project's settings') and names the concrete backing file (med-lit.settings.json). The enumeration of setting families (research mode, max_screened, search years, fetch limit, pages per article) makes it unmistakable against siblings like create_project, list_projects, and open_project, which all deal with projects but not their configuration.

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?

'Change them only as the researcher asks' is an explicit policy for the mutation path, and combined with the schema note that omitting `changes` only shows, the read/write split is clear. What's missing is routing guidance for the surrounding workflow — e.g. that the project name comes from list_projects or that this should precede start_search — so it stops short of naming alternatives.

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