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

Annotations declare readOnlyHint, idempotentHint, and destructiveHint=false; the description reinforces this and adds domain-specific context: 'it has no destructive side effects and performs no wallet, settlement, or trading actions.' It also clarifies that it 'assembles one calculation-history row from the existing ATLAS-7 precomputed surfaces,' indicating no computation or side effects. This adds value beyond the generic 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 compact—three sentences that cover purpose, components, parameters, behavior, and usage context. The first sentence is goal-oriented and each subsequent sentence adds distinct information without redundancy. The long component list is dense but necessary for completeness.

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 tool's complexity (8 parameters, many bundled surfaces), the description covers the essential context: what it does, how to filter (ticker/CIK/date range), what mode does, and its read-only safety profile. The existence of an output schema relieves it of explaining return values. It could mention limit/offset defaults, but the schema already covers those.

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 input schema has 100% description coverage, but the description adds relational meaning: 'source_date replays one YYYY-MM-DD ATLAS-7 slice', 'source_date_from/source_date_to can page recent slices', and 'ticker or CIK narrows to one issuer.' It also explains the mode parameter's effect ('compact by default and full includes source_fields_json'). This goes beyond bare parameter names.

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 a specific instruction: 'Use this read-only tool when agents need the complete ATLAS-7 calculation bundle for an issuer and source_date.' It names the resource ('complete ATLAS-7 calculation bundle'), the verb ('assembles'), and enumerates the included surfaces (covenant stress, company fundamentals, peer ranking, alpha signals, etc.). This distinguishes it from narrower sibling tools by emphasizing completeness and the historical, point-in-time context.

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?

It states when to use: 'when agents need the complete ATLAS-7 calculation bundle for an issuer and source_date' and 'Use this before historical report rendering so agents do not mix latest-only fields into a historical answer.' It does not explicitly name alternative tools or state when not to use it, but the historical-report context provides a clear usage boundary.

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