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

No annotations are provided, so the description carries the full behavioral burden. It does usefully define the semantics of non-obvious status values ('superseded', 'supersededByRunId', 'draft_ready'), which is genuine added context, but it omits scope questions (per-project only?), auth needs, and pagination behavior.

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 purpose, then two tightly packed sentences covering return fields and status semantics. Every sentence carries information, though the status explanation is dense enough to read as a run-on.

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 no output schema, the description takes on the job of describing return contents and does so competently, including an otherwise opaque status meaning. Pagination defaults are left to the schema, which is acceptable, but usage framing remains thin.

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?

All three parameters (cursor, agentKey, pageSize) are fully documented in the schema at 100% coverage, so the baseline is 3. The description adds no syntax, format, or filtering semantics beyond what the schema already states.

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 ('List') plus resource ('project managed-agent runs') and enumerates the fields returned (status, timing, credits, tokens, agent identity). It is clear what the tool does, though it never explicitly distinguishes itself from siblings like devtune_get_agent_run (single run) or devtune_list_agent_picks_runs.

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?

There is no statement of when to use this tool versus the single-run getter or the agent-picks run lister. The status semantics hint at context but do not tell an agent when this listing is the right call.

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