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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the mutation and retry profile is covered. The description adds genuinely non-obvious behavior beyond that: the result is captured as a *pending human-review* Brief decision with no automatic approval and no tool authority, and ties/minority outcomes are accepted. It does not say what state is overwritten or what happens on stale revisions, but it is well above the annotation baseline.

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 filler, with the operation and its outcome front-loaded and the authority caveat placed where it will be read. Every clause carries distinct 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?

For a destructive, idempotent 6-required-parameter mutation with no output schema, the description covers the outcome and approval semantics but omits failure/stale-revision behavior and any indication of what the call returns (e.g., a decision identifier). It is adequate but leaves real gaps for a high-consequence write.

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 two required parameters (base_revision, brief_revision) have no schema description at all. The description clarifies one by naming the "Brief revision" and the "selected option", but says nothing about base_revision's role (likely an optimistic-concurrency check), nor does it correct the schema's misleading copy-pasted text that labels poll_id and option_id as "Caller-generated UUID identifying one operation".

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 uses a specific verb+outcome ("Freezes the current poll result... as a pending human-review Brief decision") for a named poll and option, which is far more informative than the tool name alone. It implicitly distinguishes itself from read-only siblings like list_polls or vote_poll, though it never explicitly names an alternative such as propose_decision or open_decision.

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 or when-not-to-use guidance, no prerequisites (must the poll be closed? must the caller be the poll owner?), and no comparison against siblings like vote_poll, propose_decision, or propose_relay_decision. The agent must infer timing and preconditions from context alone.

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