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

Annotations already cover the safety profile (readOnly, idempotent, openWorld=false), and the description adds substantive behavior: the minimum-cell rule and suppression of small cells, publication scope (CFPB HMDA 2025, actions 1,2,3, loan_type 2), and an explicit not-a-prediction caveat. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with ANSWERS questions, then PARAM, Returns, and NOT FOR blocks, so an agent can scan quickly. Dense and mostly waste-free, though the quoted example questions add retrieval-oriented verbosity rather than direct instruction.

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 no output schema, the description carries the return-value burden and does so reasonably, describing per-cell gap changes plus cell counts and the minimum-cell rule. It could specify the response shape or pagination more concretely, but for a single-optional-param read tool it is nearly complete.

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?

Only one parameter and schema description coverage is 100% – the schema already documents name, 20-char LEI, and the omit-to-list-all behavior. The description's "PARAM: lender name or slug" adds a 'slug' phrasing not in the schema, but otherwise does not deepen parameter meaning beyond structured data. Baseline 3 is appropriate.

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 and resource: returns how a lender's peer-adjusted denial gap varies across published cells (state x loan amount x income x DTI x CLTV), with cell counts and the minimum-cell rule. The cell/conditional framing distinguishes it from flat siblings like get_lender_denial_stats and get_metro_lender_gap without requiring a schema read.

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?

Provides explicit trigger questions ("does this lender's strictness depend on loan size or leverage") and a clear exclusion block ("NOT FOR: suppressed small cells, or any individual prediction"). It stops short of naming which sibling to use instead for metro-level or summary views, so it is clear context plus exclusions rather than full alternative routing.

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