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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds critical safety context: 'never stores data or submits to MyTax' and 'output remains review-gated'. This gives the agent concrete expectations about side effects and approval flow, which is valuable beyond the structured hints.

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 two sentences long, information-dense, and front-loaded with the main purpose. Every clause adds value, and there is no redundant restatement of the tool name or title. It earns a high score for efficiency.

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?

The description covers safety and high-level purpose but is sparse for a complex tool with 11 parameters, nested objects, and no output schema. It omits details about what the returned 'Form BE fields' look like, any prerequisites beyond 'reviewed', and how to supply the required inputs. It is adequate for understanding the tool's role but not fully complete for confident 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?

With schema description coverage at only 18% and 11 parameters, the description was expected to compensate by explaining parameter meanings. It vaguely refers to 'reviewed taxpayer inputs' and 'reliefEvaluation', but does not clarify the required parameters (assessmentType, income, reliefEvaluation), their structure, or the nested object semantics. The schema itself has few descriptions, so the agent receives little guidance.

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 uses a specific verb ('Compile') and resource ('reviewed taxpayer inputs and a deterministic TaxBrain relief evaluation into source-linked Form BE fields'), clearly distinguishing it from sibling tools like assess_form_b_2025_readiness or search_tax_authority. It precisely communicates the tool's role as a draft preparer.

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 when to use this tool: after taxpayer inputs are reviewed and a TaxBrain relief evaluation exists, to produce a review-gated draft. It also clearly states non-uses ('never stores data or submits to MyTax'). However, it does not explicitly name alternative tools for other scenarios, so it falls short of a full 5.

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