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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: the June 30 snapshot semantics, the 'latest published year' default, the deposits-descending ranking, the inclusion of a sum of returned branches, and the data source. It does not mention whether results are truncated silently by the default limit of 50.

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?

A single dense paragraph with the resource and grain front-loaded, followed by the calling pattern, then the return shape and source. Every sentence carries information, though the trailing 'Source: FDIC' attribution is low-value for an agent deciding how to call the tool.

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 an output schema present, the description needn't explain return values, yet it still sketches the ranking and the aggregate sum, and it pins down units and the survey-date semantics. The remaining hole is disambiguation from fdic_branches and the truncation behavior at the default limit.

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 every parameter is already documented, including the cert-or-state+city rule and the limit default/max. The description restates the optional-parameter pattern ('cert, and optionally year, state, city') but adds no syntax or interpretation detail beyond the schema; the units note ('thousands of US dollars') describes the response, not a parameter. 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?

Names a specific resource and measurement: deposits held at each branch of an FDIC-insured bank as of June 30 of a survey year, in thousands of dollars, with address/identifiers. That is far more precise than a generic 'get deposits' label. It does not, however, distinguish itself from the closely related sibling fdic_branches, which an agent could easily confuse with this tool.

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?

It states the calling pattern ('Pass a cert (and optionally year, state, city)') and the default behavior for year, which implies when the tool applies. But there is no explicit when-to-use/when-not guidance and no routing to alternatives such as fdic_branches (branch locations) or fdic_financials (institution-level figures) — a real gap given the crowded fdic_* sibling set.

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