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

Annotations already cover safety (readOnly, idempotent, non-destructive) and closed-world scope, so the description is free to add result-shape behavior: it discloses the five possible outcome values and that results come back newest first. It does not mention pagination limits behavior or the ignore-radius-for-areas rule (that lives in the schema), so it is strong but not exhaustive.

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 resource and scope in the first sentence, then usage, then an example — a sensible order with almost no filler. The example line partially repeats the routing sentence's intent, but it earns its place by demonstrating parameter granularity.

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 an 8-parameter geo-filtered read tool with a nested point object and an existing output schema, the description covers what it must: what is returned, ordering, the place-vs-point choice, and the sibling routing. Return-value details are correctly left to the output schema.

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 100% and every parameter carries a description, including the place/near mutual exclusion and the radius caveat, so the schema does the heavy lifting. The worked example (place="Monterey", since="2026-09-01") usefully shows the date format and place granularity in action, but adds nothing the schema has not already documented.

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 resource (verification events with their outcome types), a specific scope (within a radius of a town, county or point), ordering (newest first), and explicitly names the sibling it is not ('Use dogpolicies_changes_since for everything everywhere'). An agent can distinguish it from the cluster of similarly-named siblings without opening a schema.

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?

Gives two concrete use cases ("has anything changed around Tahoe since my last trip?", re-checking a saved itinerary) and an explicit routing rule to the alternative tool, dogpolicies_changes_since, for unfiltered use. When-to-use and when-not are both present.

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