read_declaration_draft

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

No annotations are provided, so the description carries full behavioral disclosure burden. The description only restates that it reads a draft and gives no information about behavior—whether it's a pure read, what state it expects, what happens if the draft doesn't exist, or what the return value contains. There is a substantial gap in behavioral transparency for a tool with zero annotation coverage.

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 very short—a single sentence with efficient wording and no filler. However, it's under-specified rather than well-structured for clarity; brevity is achieved by omitting useful context rather than by tight editing of rich content.

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 tool has one parameter, no annotations, and no sibling differentiation. An output schema exists (so return values aren't the description's job), and the parameter schema is self-describing. For a simple single-ref lookup, the coverage is mostly adequate, but the lack of any usage context or relationship to sibling tools (especially mutate_declaration_draft and validate_declaration_draft) leaves a notable gap.

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?

Only 1 parameter (request) wrapping a DeclarationRef object with taxpayer_alias, tax_year, and declaration_id, all required and schema-constrained. Schema description coverage is 0%, but the schema is fully self-describing with patterns and constraints. The description ('read one draft') adds minimal semantics beyond the schema—it implies a lookup-by-reference pattern that's fairly clear from the DeclarationRef structure.

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 states it reads 'one normalized synthetic declaration draft' with a specific verb (read) and resource (declaration draft). It distinguishes somewhat from siblings like mutate_declaration_draft and validate_declaration_draft, but the terms 'normalized' and 'synthetic' are jargon that don't clarify what the tool actually returns or does beyond the name itself.

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?

No guidance on when to use this vs. siblings like read_normalized_evidence or validate_declaration_draft. The description doesn't explain whether this should be called before mutation, after normalization, or what scenarios call for it. Sibling tools with related purposes ('validate_declaration_draft', 'mutate_declaration_draft') suggest a workflow, but no workflow context is provided.

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