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

The description explains the non-idempotent state mutation that the annotations only flag abstractly: it 'advances the snapshot' and is tied to a watchId created in the same MCP session. This reconciles well with readOnlyHint=false and idempotentHint=false, since the operation mutates internal state despite reading like a diff. It does not cover edge behavior such as expired/invalid watchIds or rate limits.

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?

Three short sentences with the core behavior front-loaded and the prerequisite immediately after. The 'changes since the last check' idea is stated twice (opening sentence and second-to-last clause), a minor redundancy.

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?

Covers purpose, prerequisite, session scoping, and state-advancement behavior, and an output schema exists so return-value detail is not required. Remaining gaps (error handling for a stale or foreign-session watchId) are minor for a single-parameter tool.

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?

There is a single parameter with 100% schema description coverage, and the schema already states it is the watch ID from a previous watch-address call. The description's mention of the watchId origin duplicates that, adding no syntax or format detail beyond the schema, so the baseline 3 applies.

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 verb and resource: 'Get changes since the last check for a watched address,' plus the return content (changed fields and numeric deltas). It clearly differentiates itself from its sibling monitor.watch.address by describing what happens after a watch exists.

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?

Explicitly states the prerequisite ('Use only after monitor.watch.address has created a watchId in the same MCP session') and the exclusion ('create a new watch for a new address'). An agent knows exactly when this tool is valid versus when to create a new watch.

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