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

Annotations already declare readOnly, non-destructive, and closed-world, so the bar is lower, but the description still adds real behavior: results carry lenderPartnerId and the person's sharing standing, only existing PolicyVera lenders appear, and no suggestions are offered on a miss. The empty-result behavior in particular is information the annotations cannot convey.

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?

Three front-loaded sentences that each carry a distinct fact: search inputs, result contents, and the follow-up tool. Minor redundancy in repeating the name/NMLS search key already stated in the schema keeps it from a 5.

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 still explains what a match contains, what the sharing status values mean, and what happens when nothing matches. For a one-parameter lookup with safety annotations already present, an agent has everything needed to call it and interpret the result.

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% and the single query parameter is already documented as "the lender's name or NMLS number, as the person says it." The description restates name-or-NMLS without adding format, normalization, or fuzzy-match guidance beyond the schema, so baseline 3 applies.

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 ("Searches the lenders on PolicyVera"), the search key (name or NMLS number), and the return payload (lenderPartnerId plus the person's sharing standing). That combination clearly separates it from share_with_lender, which is named as the consumer of the id.

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 establishes the workflow context: find a match here, then pass its lenderPartnerId to share_with_lender, and it rules out non-PolicyVera lenders as a source. It stops short of an explicit "use this when / do not use this when" statement or naming other lookup siblings, so it is clear but not fully routed.

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