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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so safety needs no restating. The description adds genuinely non-obvious behavior: only public prayers, location is blurred to the approximate cell centre and 'never the exact spot', and an honest empty result when nothing is nearby. That privacy and completeness behavior is exactly what annotations cannot convey.

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-loaded with the resource and its scope, then the field list, then motivating queries. The sentence is dense and slightly run-on, but each clause (privacy, kind, honesty) carries information an agent cannot get from the schema.

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 not spelling out return values would be acceptable, yet the description still characterizes them alongside privacy behavior and the zero-result case. Missing only default/radius behavior for the two undocumented numeric parameters, which is minor for a read-only lookup.

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 60%: lat/lng/city carry descriptions, while limit and radius_km have none. The description gestures at place types (street, hospital, school, church, town) which map to the city/coordinate inputs, but adds nothing about limit or radius semantics, so it neither compensates for the gap nor is required to.

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 names a specific resource (public prayers left by real believers at places) and enumerates exactly what comes back: cell centre, kind, words, Scripture, author, prayer count. It is distinguishable from siblings like pray_for_someone and find_churches_near. The retrieval verb is only implied by 'Prayers left near' rather than stated, which keeps it just short of 5.

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?

Concrete example queries ('has anyone prayed near this hospital', 'prayers left in my town', 'pray where others have prayed') make the intended use case easy to recognize. No sibling is named as an alternative and no exclusion is given, so it is clear context without explicit routing.

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