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

Annotations already cover safety (readOnly, non-destructive, closed-world), and the description adds genuinely useful context above that bar: what the return contains (reply or recap) and how to render it (verbatim vs. paraphrased with facts, links, and questions preserved). It omits whether the call blocks or what happens if the turn is still unresolved, which is a real gap for a 'check' tool.

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, zero boilerplate: the first defines what is collected, the second defines the output handling rule. Front-loaded and every clause carries information.

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?

No output schema exists, so the description usefully compensates by describing the payload (reply or recap) and the presentation contract. What remains unaddressed is the pending/not-ready state and failure mode, which matters for a name like check_pally.

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 one parameter at 100% schema coverage, the schema already documents turn_id's source and the omit-to-get-newest behavior. The description adds no syntax, format, or lifecycle detail beyond that, so baseline 3 applies.

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 (collect) and two concrete resources (a pending Pally turn's reply, or a call recap from start_call), which lets an agent distinguish it from message_pally. It never explicitly contrasts itself with sending a new message, so the sibling differentiation is implied rather than stated.

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?

Names the trigger condition clearly: use it when a turn 'was still working' or to fetch a call recap. It also encodes the alternative path implicitly via turn_id's source (message_pally or start_call). There is no explicit 'do not poll repeatedly' or 'use message_pally instead when starting a new turn' exclusion.

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