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

Even with annotations (read-only, idempotent, no side effects), the description adds meaningful behavior: unknown fields become null/empty arrays, totals and line items are never invented, and billing is fail-closed ($0.10 only on success). No contradiction with the annotations.

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 a concrete verb and precise input scope, then covers geography, input modes, failure semantics, and pricing in four tight sentences. No repetition of schema boilerplate.

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?

Covers input selection (text vs file_base64), document scope, output shape, failure behavior, billing, and geographic tuning. With an output schema present, this is more than sufficient for an agent to decide when to call the tool and what to pass.

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 reinforces that input can be either text or file_base64 but does not add meaningfully beyond the schema's own descriptions. No penalty, but no extra semantic value either.

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?

Opens with 'Parse...' plus an explicit list of document types (till slip, POS printout, supermarket receipt, M-Pesa slip) and names the stabilized output fields. This clearly separates parse.receipt from generic extract.* siblings by domain and result shape.

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 explicit when-to-use guidance ('when the document is a receipt or MoMo/M-Pesa slip') and tells the agent to prefer it over manual parsing or a generic LLM scrape. It does not explicitly contrast with the sibling parse.invoice, but the document-type framing is sufficient for most routing.

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