Cursor: inspect several runs

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuine non-obvious behavior beyond that: the 45-second execution bound, strict exact-match semantics, and the resume mechanism via remaining.fromIndex. The per-item partial-failure guarantee ('one undecidable agent does not refuse the whole call') lives in the schema rather than the description, so some behavioral context is allocated to the schema. No contradiction with annotations.

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, front-loaded with purpose and zero filler — every word earns its place. However, phrasing like 'under one 45s bound' and 'remaining.fromIndex' is cryptic shorthand that references mechanisms the description doesn't unpack, so brevity slightly trades away clarity. Still efficient overall.

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 and both parameters are fully documented in the schema, so the description doesn't need to explain return values or parameter formats. The description covers the key behavioral facts (batch scope, time bound, resume, exact-match). The cryptic tone and the lack of explicit guidance around the 45s bound (retry vs. treat as failure) leave small gaps, but for a batch tool with rich structured metadata it is largely complete.

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%, with rich descriptions for both parameters (runs: order, repeat handling, per-item result statuses; fromIndex: resume semantics). Under the coverage rule the baseline is 3. The description adds only marginal value here — the 'continue at remaining.fromIndex' phrasing lightly ties the two params together but does not exceed what the schema already documents.

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?

'Read status for up to 64 agent/run id pairs' states a specific verb (read), resource (run status), and scope (up to 64 specific pairs in caller order). This clearly distinguishes it from siblings: cursor_get_run (single run), cursor_list_runs (list all runs), cursor_wait_run (wait on runs). An agent can tell when this batch-inspection tool applies without opening the schema.

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?

The description gives operational constraints — 'Exact pairs only', 'under one 45s bound', 'continue at remaining.fromIndex unless complete' — which implicitly tell an agent how to use it (strict matching, resumable pagination). But it never explicitly states when to prefer this over cursor_get_run or cursor_wait_run, nor any exclusions. Usage context is implied, not spelled out.

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