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

readOnlyHint=true already tells the agent this is a safe, non-mutating read, so the bar is lower. The description adds the HTTP endpoint and the notion that this is the primary read surface, but discloses nothing about pagination defaults, rate limits, or result volume — gaps the schema's 'after'/'pageSize' only partially cover.

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, both earning their place: the first front-loads the resource and filter surface, the second gives intent and the API endpoint. No filler, no restatement of the tool name.

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 a 14-parameter, all-optional list tool whose schema is fully described and whose annotations carry the safety profile, the description is close to sufficient. The one real gap is that no output schema exists and the description never characterizes the returned run records or pagination contract.

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 every one of the 14 parameters is already documented in the schema; baseline 3 applies. The description's enumeration (status, task, tag, queue, schedule, time window) loosely maps to some of those parameters but adds no syntax, format, or interaction detail beyond 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?

States a specific verb and resource ('List task runs') plus the filter dimensions that scope it, and frames intent as 'the main read for what ran, and what failed?'. It is clear what the tool does, but it never names a sibling it is not — e.g. trigger_get_run for a single run or trigger_list_run_events for events — so differentiation is left to inference.

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?

'This is the main read for what ran, and what failed?' implies the default listing use case, which is a genuine routing hint. However there is no explicit when/when-not guidance, no mention of the paginated/cursor nature of the call, and no named alternative for fetching a single run or its events.

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