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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond that: '10 credits flat' (cost), the POST endpoint, and crucial semantics – statement_type is a list of canonical names, can hold more than one when a block combines statements, and is null for non-financial header blocks. This is substantial behavioral disclosure.

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 a compact paragraph front-loaded with 'Discovery'. Every clause earns its place: scope, return fields, credit cost, next step, endpoint, and documentation reference. There is no filler or repetition of schema details.

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?

For a read-only discovery tool with no output schema, the description fully covers what the agent needs: exact return fields with edge-case behavior (null header blocks, combined statements), the two valid scope modes, cost, and the natural next tool. The sibling context and annotations round out the picture, leaving no critical 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?

Schema description coverage is 100%, so the baseline is 3. The description reinforces the filing_id vs ticker+fiscal_year relationship, but the schema already documents this ('Use with fiscal_year when filing_id is omitted', 'Required together with ticker when filing_id is omitted'). The description adds little beyond what the parameter descriptions already convey.

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 opens with 'Discovery: list every statement block for one filing' – a specific verb and resource – and enumerates the returned fields: block_index, statement_type, and role_label. It differentiates itself from get_filing_statement by naming it as the follow-up for row labels, so an agent can place this tool correctly relative to siblings.

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 gives explicit scope modes ('filing_id OR ticker + fiscal_year') and explains that quarter is optional. It provides workflow guidance: 'Follow with get_filing_statement to see the exact row labels a statement uses.' It doesn't spell out when not to use this tool versus other sibling listing tools, but the context is clear enough for selection.

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