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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the marginal bar is lower. The description adds real context beyond them: an evidence verdict per agent naming unreadable sources, trial credit allowance, and scheduling restrictions during trial — all of which affect how a caller should interpret results before spending a run.

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?

Purpose is front-loaded in the first clause and each sentence adds distinct information (agent scope, verdict semantics, trial credit, archive mode). A few sentences are dense and carry secondary details (trial credit allowance, scheduling restriction) that could be tightened, but nothing is wasted.

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 and a single optional parameter, the description does the work of summarizing returned content (evidence verdicts, archivedAt, trial credit) and points to the downstream tool. It leaves the pagination/format of the list itself unspecified, which is a minor gap for a list operation.

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 100% schema coverage the baseline is 3, but the description goes further by explaining the consequence of archived: true (only archived custom agents, each carrying archivedAt) and its purpose — obtaining an agentKey for devtune_restore_custom_agent. That adds meaning beyond the schema's one-line parameter description.

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 gives a specific verb and resource ('List the code-owned and custom managed agents available to a project') and scopes what it returns ('display-only definition fields'). It doesn't explicitly differentiate itself from look-alike siblings such as devtune_list_agent_runs or devtune_run_agent, so an agent must infer the boundary, but the naming of an archive mode and devtune_restore_custom_agent anchor the intent clearly enough.

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?

'Pass archived: true to list only archived custom agents instead' states the exact condition and the follow-on tool (devtune_restore_custom_agent), which is actionable routing guidance. It also implies the primary use case (checking what a run would be missing before paying). It lacks explicit when-not-to-use guidance or comparison against devtune_list_agent_runs, keeping it below a 5.

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