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

Annotations only declare it is a non-readonly, non-idempotent, open-world write; the description adds genuinely useful behavior: permission switches default closed 'even though the owner can act there,' building is free on owned/open land, a $1 fee applies to frontier claims, and the idempotency/retry contract via a new city_credit_request_id versus falling back to X-PAYMENT. It does not describe what is returned on success or what happens if the fee charge fails.

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 purpose is front-loaded in sentence one, but the remainder is a dense run-on that jumps from permission defaults to frontier economics to gazette protocol to credit preflight to idempotency, forcing the reader to untangle several distinct workflows. Every topic is relevant, but grouping and ordering could be tightened considerably.

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 7-parameter write with no output schema, the description covers prerequisites, fees, defaults, and retry semantics well. However it never states what a successful call yields (new place id? location?), how errors surface, or what 'safe characters' means, leaving real gaps for an agent that must verify the outcome of a mutating call.

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 only 29%, yet the description compensates for most of the 7 params: name/description length limits, parent_id null-or-world-id meaning, the three permission switches and their closed defaults, and the semantics of city_credit_request_id (new id to spend a credit, omit to use X-PAYMENT, take the fresh suggested_request_id). It leaves 'safe characters' undefined and does not explain the request-id pattern constraint beyond the 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?

Opening sentence gives a clear verb+resource ('Found a place') plus the name and description constraints, so an agent knows the operation immediately. It distinguishes the frontier/parent_id null case from ordinary place creation. It does not explicitly contrast itself with sibling mutation tools like place_edit or claim_world, and terms like 'safe characters' and 'notes, things, building' assume domain knowledge.

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?

Strong explicit routing: call browse with view=gazette before work in Room #454, call credit_preflight before confirming a credit-funded frontier claim, and call front_door when lost — each with a stated precondition. It also states when to send city_credit_request_id versus omit it. What's missing is guidance on when to choose found over siblings such as place_edit or claim_world.

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