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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds real value beyond that by explaining the lifecycle meaning of "superseded", identifying supersededByRunId as the pointer to the replacing run, and clarifying that partially retired runs remain draft_ready. It stops short of describing result ordering, default page size behavior, or what happens for runs not yet settled.

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?

The purpose statement is front-loaded in the first sentence, and the two follow-up clauses on superseded states are compact and each carry distinct meaning. There is no filler, though the status-semantics sentences are only loosely connected to the listed outputs and could have been ordered to match the field list.

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schema, the description carries the burden of explaining the returned fields and does so for the ambiguous ones (status/superseded, credit consumption, agent identity). Pagination is handled by the cursor/pageSize schema entries, but nothing tells the agent how filtering by agentKey interacts with results or how large result sets should be walked, leaving a modest gap.

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%, so all four parameters are already documented in the schema and the baseline of 3 applies. The description adds no parameter-level meaning at all, notably leaving the awkward limit/pageSize aliasing ("the same setting as pageSize. Send either.") and the agentKey roster/custom-agent filter semantics entirely to the schema.

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?

The description opens with a specific verb+resource ("List project managed-agent runs") and enumerates the payload (status, timing, settled credit consumption, token usage, agent identity), which is far more informative than a restatement of the name. It does not explicitly contrast itself with the sibling devtune_get_agent_run for single-run retrieval, so sibling differentiation is implied by plural/listing phrasing rather than stated.

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 when-to-use or when-not-to-use guidance, no mention of paginating versus fetching a specific run via devtune_get_agent_run, and no prerequisites called out. The only contextual content is a definition of the "superseded" status, which is domain semantics rather than invocation guidance.

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