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

The description adds context beyond the annotations: the position is 'an opaque string we store verbatim and never interpret,' the tool is free, and authentication can be done via Authorization header or agent_key argument. These behavioral details are not present in the readOnlyHint/idempotentHint/destructiveHint annotations, enriching agent understanding of side effects and invocation constraints.

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 description is concise (four sentences) and front-loads the primary purpose. However, FREE is stated twice ('FREE.' and 'FREE — this tool never charges.'), which is redundant and slightly violates the 'every sentence earns its place' principle. Otherwise, the structure is clear and efficient.

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 simple write tool with no output schema, the description adequately covers the core behavior, auth, HTTP route, and opaque position handling. It does not explicitly state overwrite behavior (e.g., calling it again replaces the prior position), but the term 'record' implies this. Overall, it is sufficiently complete for an agent to select and use the tool correctly.

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%, so all five parameters already have detailed meanings. The description reiterates that position is 'opaque' (already in the schema) and mentions agent_key as an alternative authentication method (also in the schema), adding no new param semantics beyond what the input schema provides. Thus baseline 3 is appropriate.

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 begins with a specific verb-resource pair: 'Record how far you got through a stream, feed or table,' making the tool's function unmistakable. It also differentiates from siblings like watermark_get by focusing on writing progress, and the phrase 'so the next invocation knows where to start' clarifies the downstream purpose.

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?

The description clearly conveys the use case—recording progress through a stream, feed, or table—and implies it should be called after consuming data. However, it does not explicitly name alternatives or explain when not to use this tool (e.g., for ephemeral checkpoints use checkpoint_put), so it falls short of a 5.

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