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

The description discloses immutability ('immutable'), read-only nature ('List'), idempotent behavior (implied by list operation with no side effects), authentication requirement ('Requires a paid CarrierScore API key'), retention rules for different key tiers, and error conditions (403/400). These go beyond the annotations (readOnlyHint, idempotentHint, openWorldHint) by providing specific behavioral details about key tiers, errors, and the nature of the data.

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 well-structured with a clear first sentence defining purpose, followed by usage guidance, key tier info, parameter list, return structure, and error handling. Each part adds value. While slightly long, it front-loads the core purpose and is efficiently organized with bullet-like formatting for parameters and returns.

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 has 3 parameters (all documented), an output schema exists (the description even provides the structure), and the tool is a straightforward list operation, the description is complete. It covers purpose, usage context, key tier differences, parameter details, return format, and error scenarios. No additional information seems missing for an agent to correctly select and invoke this tool.

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 covers all three parameters with descriptions (100% coverage), so the baseline is 3. The description adds value by clarifying optionality ('optional') for dot_number, specifying the default for limit ('default 50' which is not in the schema), and explicitly stating the range '1-500' and format for since ('YYYY-MM-DD; only entries generated on/after this date (UTC)'). This extra context raises the score above baseline.

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 clearly states the tool lists immutable audit-archive entries for the caller's API key, specifying the verb 'list' and the resource 'audit-archive entries' with details about content (every Montgomery evidence report) and ordering (newest first). It distinguishes from siblings like montgomery_file (which likely retrieves a specific file) and verify_evidence (which verifies evidence), as it focuses on listing entries for the caller's key.

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 explicitly states when to use the tool: 'Use it to answer which carriers did we generate evidence for, and when? and to find the entry id to cite or verify for a given carrier and date.' It also provides context about key tiers (Monitor vs Compliance keys seeing different retention). However, it does not explicitly exclude alternatives or contrast with sibling tools like montgomery_file for downloading files or verify_evidence for verification.

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