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

Adds real context beyond annotations: watchers consume the workspace's Refix usage, are visible to everyone in the workspace, and the agent is instructed to disclose both. The alerts routing behavior (mcp_assistant keeps alerts in Refix for refix_list_findings, with no Slack post or email) is also disclosed. Minor gap: it doesn't say whether the watcher starts running immediately or what the creation response contains, though an output schema exists.

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 dedupe instruction is front-loaded and every sentence carries information. It is dense and the alerts clause is a long semicolon chain, but nothing is redundant with the schema or annotations.

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 mutation tool with annotations (readOnlyHint false, idempotentHint true, destructiveHint false) and an output schema, this covers preconditions, side effects on usage and visibility, and alert delivery. What remains unsaid — return shape and immediate execution behavior — is carried by the output schema and annotations.

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 75% and already documents timezone, objective, and idempotency_key, so the baseline is 3. The description goes beyond that by explaining what each alerts value implies operationally ('mcp_assistant' keeps alerts in Refix for refix_list_findings; 'slack'/'email' must match alert_channel from refix_get_context), which the enum alone does not convey.

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 ("Create a Refix watcher") and then defines what a watcher actually is: something that carries a goal, keeps working against connected data, and reports findings to a chosen place. That definition, plus "ongoing goals, not one-off questions," lets an agent separate it from refix_investigate and refix_update_watcher without opening schemas.

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 an explicit precondition ("Call refix_list_watchers first and do not create a duplicate") and a clear when-to-use rule (ongoing goals, not one-off questions). It doesn't name the alternative tool for one-off questions by name, so the routing to refix_investigate is left to inference rather than stated.

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