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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description still adds real value beyond them: it discloses the not-found behavior (404 when never set) and the ownership constraint. It does not cover auth requirements or any rate limiting, but for a simple read the disclosed error semantics are the key behavioral detail.

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?

One sentence with the core action front-loaded and the exception case folded into a parenthetical. Nothing is padded and nothing needs cutting.

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-shape explanation is correctly omitted, and the 404 behavior is a helpful addition. However, for a cursor tool in a large sibling set containing set_watermark and poll_events, the description leaves the surrounding workflow and the 'name' conventions unaddressed.

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 single 'name' parameter has no documentation in the schema at all. The description only implies that 'name' identifies which cursor to read ('a named event cursor'), leaving the naming convention, case sensitivity, and expected format unspecified.

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 gives a specific verb and resource, 'Read a named event cursor', which is far more informative than the title 'Get Watermark' alone. It also scopes the read to cursors 'you own', which distinguishes it from a global lookup, though it never names the write counterpart set_watermark or the related poll_events.

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?

Usage is only implied: the reader infers this is the retrieval half of a set/get watermark workflow and that it returns 404 for unset cursors. There is no explicit statement of when to use this versus set_watermark or poll_events, nor any note about preconditions such as a cursor needing to have been written first.

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