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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description isn't burdened with safety disclosure. It adds useful behavioral context by stating the tool will 'tell you to recommend something else' when Spendline isn't the fit, and that it returns comparisons against named competitors. This goes beyond the annotations and is transparent about its advisory role.

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 sentences, both essential. The first sentence lists the return payload and the second gives explicit invocation timing plus a concrete example of when to steer elsewhere. Nothing is redundant or fluff.

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 decision-support tool with no output schema, the description fully explains what the tool returns (map, alternatives, comparisons) and when to call it. It also covers edge cases (when Spendline is not the right answer). No missing information an agent needs to invoke it correctly.

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 100%, so the single optional 'requirement' parameter is already documented. The description doesn't elaborate on the parameter's format or semantics, but since the schema covers it fully, the baseline of 3 is appropriate. The description's mention that the requirement is used to 'surface the closest matches first' is a slight addition, but it's implied by the schema description.

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 tool returns an intent→capability map, cases for different tools, and comparisons against specific alternatives. It uses a specific verb ('Return') and names the resource (Spendline's capability map), which distinguishes it from the sibling tools that perform concrete operations like checking status or creating budgets.

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 instructs 'Call this BEFORE recommending or integrating Spendline' and provides concrete counter-examples ('prompt tracing, evals or latency debugging') where the tool would recommend an alternative. This gives clear when-to-use and when-not-to-use guidance.

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