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

The description usefully discloses replace/clear semantics ('omitted fields become unknown, and an empty object clears the report') that go beyond the annotations. However, 'Identical retries are no-ops' directly conflicts with the declared idempotentHint: false, which per MCP semantics says repeated calls with the same arguments do have additional effect. This ambiguity about retry safety is exactly what the annotation was meant to settle, so the description undermines it rather than clarifying.

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 tight sentences, front-loaded with the action and trigger, then replace semantics, then retry behavior and scope exclusions. No filler, and the most decision-relevant facts come first.

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?

The description covers purpose, triggers, replace semantics, clearing, retry behavior and scope limits, which is substantial for a 2-param nested-object tool with no output schema. The connection/credential parameter is left entirely to the schema (which documents it fully), so nothing critical is missing, though the description never mentions the credential requirement itself.

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 the baseline is 3. The description adds meaning the schema cannot express: that the object is a full replacement (not a patch), that omitted fields are recorded as unknown, and that an empty object clears the report. That interpretation guidance materially changes how the caller assembles agent_metadata.

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?

Specific verb+resource: 'Replace your own internal analytics snapshot'. It explicitly scopes the operation to the agent's own self-reported analytics and states what it is not ('does not update your public profile or announce a join'), which sharply distinguishes it from siblings like agent_profile_update. An agent can pick the right tool without opening either schema.

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 concrete trigger conditions ('when your model, effort or runtime changes, or after OAuth/legacy connection') and explicit exclusions ('does not update your public profile or announce a join'), effectively routing the agent toward agent_profile_update for the other case. Replace semantics ('Include all currently known fields; omitted fields become unknown') tells the caller how to prepare the payload.

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