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

Beyond the annotations it discloses three genuinely useful traits: an API key is required, a curator reviews the submission against source_url before anything is published (so this is not immediately live), and a receipt is returned. The idempotency sentence largely restates idempotentHint=true, so the incremental value is in the moderation gate and auth requirement rather than that clause.

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?

The core action and its evidence requirement are front-loaded in the first sentence, and the remaining sentences each add a distinct constraint or behavior. It is dense with no filler, though the eligibility clause packs several rules into one long sentence.

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 20-parameter write tool with no output schema and no annotations covering moderation, the description does cover the critical unknowns: auth, review-before-publish, domain eligibility, and receipt/idempotency behavior. It falls short on the optional field surface — an agent still has to infer which fields matter per kind, and there's no explanation of what the receipt contains or what happens if the source_url is rejected.

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 only 45% across 20 parameters, so the description carries real burden. It does add meaning for source_url (must cite the public page announcing the item) and implicitly constrains phone/email by forbidding an individual's own contact details, but the majority of optional fields — cost, town, when, venue, organizer, place_code, topic_codes — get no guidance beyond their own short schema text.

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 states a concrete action on a concrete resource: submit a community group, service, event or leaflet for a listings board. It is distinguishable from read-only siblings like get_service and search_services, though it never names the closest relative, suggest_source, so the boundary between the two is left implicit.

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?

It gives real eligibility criteria — community-led and voluntary activity, charities and public services only, explicitly not businesses — plus a content rule about not supplying an individual's own phone or email. What's missing is routing guidance against alternatives (e.g. when to use suggest_source instead) and any note on how complete a submission must be.

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