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

Annotations already declare read-only, idempotent, and non-destructive. The description adds key behavioral detail: source input is omitted by default and only returned when include_input=true, along with the specific return contents, which is useful given the absence of an output schema.

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?

Two concise sentences with no redundancy. The main purpose is front-loaded, and the include_input nuance is placed naturally as a secondary clause. Every word is informative.

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 read-only get-by-id tool with two parameters and no output schema, the description provides all necessary details: what data is returned, the ownership constraint, and the optional input behavior. No critical information is missing for correct invocation.

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?

The description clarifies that include_input requests the decrypted source text and that the default is omitted, complementing the schema description. run_id is a standard identifier with no ambiguity. With 50% schema coverage, the description adds meaningful context for include_input.

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 clearly states the verb 'Get' with a specific resource: 'one private Accounting run owned by the caller', and enumerates the exact data returned (deterministic estimates, disclaimer, engine revision, audit timestamps). This distinguishes it from list_accounting_runs, create_accounting_run, and delete_accounting_run without ambiguity.

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 implies single-object retrieval vs. listing alternatives and specifies the caller ownership, plus the conditional behavior of include_input. However, it does not explicitly mention alternative tools or when-not-to-use conditions, relying on the standard get-by-id pattern.

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