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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them by disclosing the provenance semantics of the cost_basis column, including why two providers differ (no historical billing API, negotiated vs list rates) and the accuracy caveat for static-rate figures. That is precisely the behavioral context an agent needs to avoid misreporting numbers.

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 sentences, entirely front-loaded: purpose first, then the cost_basis enum semantics, then the reporting directive. The enumeration is dense but every clause conveys a distinct distinction the agent must preserve when summarizing results.

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?

There is no output schema, yet the description compensates by explaining the returned fields' meaning and their reliability implications. For a zero-parameter read tool with full annotation coverage, nothing material is missing.

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 tool takes zero parameters, for which a 4 is the baseline. The description instead spends its budget documenting the shape and meaning of returned rows, which is the more relevant semantic content here.

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 ('List the cost-source providers ... enabled for this account') and immediately enumerates examples (AWS, GCP, Anthropic), so the agent knows exactly what a call returns. It is cleanly distinguished from siblings like list_cost_source_tag_keys or list_cost_tags, which operate on different objects.

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?

It gives clear interpretive guidance — 'Qualify any total that includes an estimated source rather than reporting it as billed spend' — which tells the agent how to use the output downstream. It stops short of naming when-not-to-use conditions or sibling alternatives, but the calling context is unambiguous.

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