refresh_cases

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

With annotations only declaring readOnlyHint=false, openWorldHint=true and idempotentHint=true, the description adds real behavioral value: it discloses that cap-exceeding articles are deferred rather than dropped, that unreachable sources are reported by name and retried, and that it merges into existing lawsuits (a mutation). It stops short of describing result/output shape beyond the error-reporting note.

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 pipeline in the first sentence, then compact per-parameter clauses. It is longer than a typical description but every clause corresponds to an undocumented parameter or a behavior (deferral, retry) that an agent needs, so the length is earned.

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?

For a 4-parameter mutation tool with no output schema and 0% schema coverage, the description covers parameters, external I/O, failure handling, and partial result reporting. The main remaining gap is a fuller account of what a run returns or how progress is observed.

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 carries the full burden and does so: it defines sources with the concrete allowed values (prnewswire, businesswire, globenewswire) plus the 'all three' default, days as a look-back window, max_fetch as a per-source body cap, and include_courts as a CourtListener sweep limited to nature of suit 850. This supplies semantics the schema's bare typed properties entirely lack.

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 concrete verb+resource pipeline: read newswires, discard non-filed cases, extract ticker/class period/deadline, and merge announcements into lawsuits. An agent can tell this is the ingest/refresh job rather than a read tool like list_cases or search_announcements, though the description never names a sibling to sharpen the boundary.

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?

Usage context is implied by 'Run one pass' and by the parameter semantics, but there is no explicit statement of when to call this versus get_case/list_cases/search_announcements, nor any prerequisite or exclusion. The operational notes (deferred over cap, retried on failure) hint at usage but do not route the agent among alternatives.

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