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

The description discloses many non-obvious behaviors: raw reports are not persisted, restarting the service ends recovery, external OCR sends data to Google Document AI outside Israel, local-only is the default, and terminal failures never restart the same operation. These add significant context beyond the annotations (readOnlyHint, openWorldHint, etc.), covering data handling, failure semantics, and external interactions.

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?

The description is dense but not excessively long. It front-loads the main purpose and then details conditions. However, it packs many caveats into a single paragraph, which could be more scannable with bullets. Still, each sentence adds value and the overall length is appropriate for the tool's complexity.

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?

Given the high complexity (6 parameters, nested objects, external OCR, security considerations, and an output schema), the description is thorough. It covers operational constraints, data privacy, recovery behavior, and legacy paths. The output schema handles return values, so the description focuses on critical usage details, making it complete for an agent to call this tool 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?

The description adds meaning for operation and external_ocr, explaining their use cases and constraints. However, the required security_challenge and security_proof parameters lack any explanation, and the schema also has no descriptions for them. With schema coverage at 50%, the description partially compensates but leaves the security fields unexplained, which is a gap for correct invocation.

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 action ('Analyze') and the resource ('PDF, JPEG or PNG balance report'), and specifies the output format ('structured facts and readable Hebrew text/HTML'). This distinguishes it from sibling tools like delete_report_analysis_result and get_report_analysis_result, which have different verbs and purposes.

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 provides detailed guidance on when to include the operation parameter (for recovery/replay) or omit it (legacy immediate-only), and when external OCR is allowed (with agent attestation or legacy approval). It does not explicitly contrast with sibling tools, but those are clearly different actions (delete, get), so the context for this tool is clear.

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