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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses material behavior: the 2027 figures are projections under each limit's statutory indexing formula until the IRS publishes its notice and are labelled as such; a non-governmental 457(b) has no catch-up; the Roth catch-up wage rule determines how much of the catch-up must go in as Roth; and a deferral saves no Social Security or Medicare tax. These are non-obvious facts an agent cannot derive from the schema or annotations.

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 key fact — what limit is returned for which plans and years — is front-loaded in the first clause, and the caveats (projection status, not tax advice) are placed at the end where they belong. The middle is one very long enumerated sentence that is dense and hard to parse, but given eight parameters and a complex tax domain, most clauses carry real information.

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 burden of describing the result, and it does enumerate the components returned (base limit, catch-ups, SIMPLE higher limit, Roth catch-up portion, the amount a deferral is figured on). It also states that the tax year and projection status are reflected in the result. Minor gaps remain, such as whether the response is a single figure set or a structured breakdown.

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 (age, plan, wages, amount, tax_year, roth_catchup, higher_limit_simple, non_governmental_457) is already documented in the schema, including the age-60-63 catch-up and the projection caveat. The description largely restates these in prose rather than adding new semantics, so the baseline of 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?

The description opens with a specific verb and resource: 'Returns the 2026 or 2027 elective-deferral limit for a 401(k), 403(b), governmental 457(b), the TSP or a SIMPLE IRA at an age.' Enumerating the plan types and the computed sub-amounts (base limit, age-50 catch-up, ages 60-63 catch-up, SIMPLE higher limit, Roth catch-up portion) makes the tool clearly distinguishable from the sibling IRA deduction tool without opening any schema.

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 only implied by the parameter set: an agent can infer this applies to workplace-plan deferral limits for a given age and wage level. There is no explicit when-to-use/when-not statement, no mention of the sibling tools (e.g., ira_deduction_and_roth_limit, calculate_rmd), and no prerequisites such as filing status requirements. 'Not tax advice' is a disclaimer, not guidance.

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