nws_public_speaker_preview_change

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

With no annotations, the description carries the full burden. It does usefully disclose the 10-minute expiry of the returned confirmation ID and flags that leave_circuit can remotely delete data. However, it never clarifies whether 'preview' is a strict dry-run for every action — sync_congregations_and_speakers reads like a real import — nor does it state required permissions or what happens when the confirmation window lapses.

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?

Front-loads the purpose and the confirmation-ID return in one sentence, then enumerates actions compactly. The action list is dense with parenthetical parameter hints but every clause carries information; no 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?

An output schema exists, so return values need not be described. Still, for a 5-parameter, zero-coverage, unannotated mutation-adjacent tool, an agent is left without the required circuit_id's meaning, without confirmation that the listed actions are the full valid set (the schema declares action as a plain string with no enum), and without clarity on which actions are safe reads versus side effects.

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 0%, so the description must compensate. It adds real meaning for circuit_type (primary or guest), congregation_id (used with approve/deny) and remotely_delete_data (scoped to leave_circuit on the approved primary circuit), but leaves the required circuit_id completely unexplained and doesn't say which parameters each action requires versus ignores.

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+resource ('Preview a public-speaker circuit change') and adds the distinctive outcome, a 10-minute confirmation ID. It implicitly separates itself from nws_public_speaker_commit_change / cancel_change through the word 'preview', but never names those siblings, so the differentiation is inferred rather than explicit.

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?

The description implies the preview→commit flow by advertising a 10-minute confirmation ID, but gives no explicit when-to-use guidance, no statement that commit_change must follow, and no exclusions or prerequisite conditions for choosing this over the generic nws_preview_change or the public-speaker commit/cancel siblings.

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