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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real behavior: duplicate names resolve to the largest institution with the others listed, and a documented escalation path to get_institution. Return contents are described only loosely ('which finance apps likely connect').

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 tight sentences with the core purpose front-loaded and the disambiguation rule attached to the parameter that triggers it. No filler, though the 'call get_institution with the right URL' clause is a little compressed and the `app` sentence largely echoes the schema enum.

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 read-only lookup with four fully documented parameters and no output schema, this covers the decision points an agent needs: disambiguation, state narrowing, app focus, and where to go on ambiguity. Only the return shape and the boundary with search_institutions remain underspecified.

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%, so the baseline is 3. The description does add purpose for `state` (narrow common names) and `app` (focus on one app) beyond the enum listing, but it does not explain `kind` or add syntax details the schema lacks.

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: find a bank, credit union or brokerage by name and report which finance apps likely connect to it. That is far more than a restatement of the name. It does not, however, contrast itself with the close sibling search_institutions, so an agent must infer which one to pick for a partial-name lookup.

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?

Gives concrete operating guidance: pass `app` to narrow to a single app, pass `state` to disambiguate common names, and fall back to get_institution with the right URL when the name is ambiguous. Missing only an explicit statement of when this beats search_institutions.

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