poll_output

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

With no annotations, the description carries the full behavioral burden and largely fails it. It does not disclose whether polling blocks, what happens once the process exits, how much output is returned per call, or the read-only nature of the operation.

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?

A single short sentence with no padding, and the verb+resource are front-loaded. It is efficient, though arguably terse to the point of under-specification rather than optimized conciseness.

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?

There is no output schema and no annotations, so the description should explain what a poll returns (a chunk of stdout/stderr? current status? offset behavior when using since). None of that is present, leaving the agent unable to predict the call's result.

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 both process_id and the since byte offset are already documented by the schema. The description adds no syntax, defaults, or interpretation beyond that, which matches the baseline 3 for a fully-covered 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 (poll) and resource (output from a background process), so the basic action is unambiguous. However, it does not differentiate from the sibling read_output or connect itself to start_process, leaving the agent to infer which of the two output-reading tools applies.

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 explicit when-to-use guidance, no stated prerequisites (must a process be running first?), and no mention of the closely related read_output alternative. The word 'poll' implies repeated checking, but the agent must infer that from the name alone.

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