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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral context beyond them: the authorization model, that no customer IDs or portal bearer tokens are accepted, that results are limited to records the portal has loaded rather than a lifetime archive, and what to do when verification lapses. That is exactly the extra layer annotations cannot carry.

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?

Front-loaded with the authorization gate, then scope, then failure mode; every sentence is substantive and none is filler. The authorization theme is restated a few times ('an MCP connection alone never authorizes history', 'no customer IDs or portal bearer tokens'), which is defensible emphasis for a high-risk operation but trims a point for density.

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?

With an output schema present, the description need not explain return values, and it covers everything else an agent needs: who may call it, what proof is required, what the result set covers, and how to recover from expired verification. Nothing material is left to inference for a 4-parameter, zero-required-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?

Schema description coverage is 100%, so the schema already documents limit, query, status, and history_access_token, making 3 the baseline. The description goes slightly beyond by stating the token is private proof attached automatically and by rejecting customer IDs and bearer tokens, which steers the agent away from inventing or substituting parameters — marginal but genuine added meaning.

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 precise verb+resource — searching the authenticated account's service records by repair keywords, date text, and status — and immediately separates itself from customer_lookup and open_customer_portal. An agent can tell what this does and what it does not do without opening the 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?

Explicitly names the triggering context ('from the customer card or browser bridge after customer_lookup verifies SMS'), the required precondition (private proof), the alternatives for shared agents (history from customer_lookup, or open the customer portal), and the recovery path when verification expires (use customer_lookup again). It even states a negative rule: an MCP connection alone never authorizes history.

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