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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds two things beyond them: an access scoping caveat ('accessible' runs only) and a return-shape disclosure ('compact summaries, not result payloads'), which matters since no output schema exists. It stops short of describing result ordering or what fields the summary contains.

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 sentences, zero waste, with the core capability front-loaded and the return-shape caveat following immediately. Every sentence earns its place.

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 an 8-parameter, 0%-coverage list tool with no output schema, the description covers the what but not the how: required pagination parameters, date timestamp format, and the meaning/narrowing of q are all unaddressed. An agent can call it, but not confidently on the first try.

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?

With 0% schema description coverage, the description must carry all parameter meaning, and it partially does by mapping filters to status, workflow_id, project_id, created_after/created_before and q. But it never mentions limit/offset — both of which are required — and gives no date-format or query-syntax detail, leaving a real gap.

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 and resource ('Find accessible workflow and batch runs') and enumerates the filterable dimensions (status, workflow, project, date, name). It implicitly distinguishes itself from siblings like get_workflow_run and get_workflow_results by noting it returns 'compact summaries, not result payloads', though it never names those siblings.

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 is implied by the filter list and the 'not result payloads' caveat, which tells an agent this is a discovery step before calling get_workflow_run or get_workflow_results. However, there is no explicit when-to-use/when-not guidance and no mention of list_jobs as the alternative for non-workflow jobs.

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