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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavior: unauthenticated calls return only counts and dollars by tier, while a Tensorust key unlocks named rows ordered tier 1 first. That access-tiered return behavior and the ordering guarantee are not in any structured field. It stops short of stating pagination or result caps.

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 purpose is front-loaded and the enumeration is largely justified by 0% schema coverage, but the second sentence is a single dense run-on that dumps a 17-value code list mid-stream. The two code vocabularies run together without labels tying them to parameters, which costs readability.

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 6-parameter, zero-documented-schema, no-output-schema tool, the description does cover the qualifiers (tier, state, agency text, eight_a, both code sets) and describes the shape of the response under both access tiers. The remaining hole is the ambiguous code-to-parameter mapping.

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 0%, so the description must carry the parameter burden, and it does supply the tier range (1-3) and two long value vocabularies (set-aside codes SBA/8A/8AN/SDVOSBC/WOSB/HZC; explanation codes RND/MARINE/UNION/...). However, it names them 'set-aside code' and 'explanation code' without mapping either to the actual parameter names `setaside` and `code`, leaving the agent to guess which enum belongs to which field.

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 first sentence names the resource concretely (Performance Ledger review queue), defines the population with explicit thresholds ($1M+/yr labor/R&D, $500K+ per active Form 5500 participant), and the filter sentence makes clear it is a filtered-list tool. It is clearly distinguishable from siblings like perf_firm and perf_summary by scope, though it never names those siblings to draw the contrast explicitly.

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?

Usage is implied by the filter vocabulary: an agent can infer it is for slicing the set-aside queue by tier, agency, code or state. There is no explicit when-to-use versus perf_firm / perf_recent / perf_summary, and no statement of when this tool is the wrong choice.

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