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

Annotations declare readOnlyHint=true, and the description adds contextual behavior beyond that: it reveals the returned fields, explains the meaning of needs_sync, and clarifies the estimated filter semantics. This gives the agent a clear model of what the tool returns and how to interpret it.

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?

Three sentences, each earns its place: the first describes the return payload, the second explains needs_sync and a downstream action, and the third explains filtering. No redundancy or filler.

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 list tool with no output schema, the description sufficiently covers what is returned, how to interpret the special field, and how to filter. It also connects to a sibling tool, making the chain of operations clear.

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?

The input schema already covers all parameters thoroughly (100% coverage). The description adds a useful conceptual mapping of estimated to 'done or left', which helps the agent reason about the parameter's purpose without repeating schema details.

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 clearly states the tool returns tasks of a poker game and specifies the exact fields (estimate, individual votes, tracker key, link). It also distinguishes the tool's output from the sync tool by explaining how needs_sync feeds into poker.game.task.sync.

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?

Provides explicit guidance on when to use the output: tasks with needs_sync should be fed to poker.game.task.sync. It also explains how to use the estimated filter to narrow results to done or remaining tasks, making alternatives and follow-up actions clear.

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