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), and the description adds genuinely new context: result ordering, exclusive scoping to the caller's own tasks, and a tier/plan gate with sample rejection. The default-to-pending disclosure is the most consequential behavioral hint, since it means cancelled and completed tasks are invisible unless requested.

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 with the scope and ordering front-loaded before the filtering and tier caveats. The inline enum restatement is the one mildly redundant element against a schema that already defines it, but nothing is padded.

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, so return-shape explanation is rightly omitted, and for a three-optional-parameter read tool the remaining needs are scope, ordering, defaults and access gating — all present. Only a brief note on what 'caller's own' means (key vs agent identity) would make it fully self-contained.

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 coverage is 67% and the status parameter already carries its own description and enum, so repeating the enum values in prose adds little. The description adds no meaning for `limit` (default 20, max 100) or `cursor` beyond what the schema documents, though it does usefully flag that status defaults to pending, which a naive call would miss.

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 (paginated listing of scheduled/deferred tasks), the exact scope ('the caller's own'), and the ordering ('newest-first'). The 'own' scoping plus the deferred-task framing separates it from generic listing siblings such as list_agent_runs without the agent needing to open a 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?

Usage is only implied: the status filter and default are described, and the tier note signals eligibility, but there is no statement of when to choose this tool over alternatives (e.g. list_agent_runs) or when not to. Adequate for a simple read-only list, but the agent must infer the routing.

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