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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real context: the output preserves source URLs, locators, search scope, coverage, and 'explicit non-inference rules,' the last hinting at a no-hallucination guarantee. That is useful but thin for an 8-parameter pipeline tool with no stated limits or auth needs.

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?

Single dense sentence, front-loaded with the core action and purpose. It wastes little, though the trailing list of preserved artifacts ('source URLs, locators, search scope, coverage...') is somewhat enumerative rather than additive.

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?

With an output schema present and full schema coverage, return-format details are not needed. However, for a complex multi-parameter tool the description omits when this step belongs in the evidence workflow and how it differs from search_evidence, leaving a meaningful 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 schema already documents all 8 parameters including identifier, q, forms, and the limit/filings caps. The description adds no parameter-level meaning beyond that, so the baseline 3 is correct.

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?

States a specific verb ('package') and resource ('the strongest relevant SEC evidence'), and specifies the audience ('an upstream AI agent'). It is clear what the tool produces, though it never names or contrasts with siblings like search_evidence or verify_claim, which operate in the same evidence-gathering space.

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 no when-to-use conditions, no prerequisites, and no alternatives. It does not tell the agent when to reach for build_evidence_pack versus search_evidence, verify_claim, or the other build_* siblings, leaving selection entirely to inference.

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