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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond that: injection-attempt detection, out-of-scope topic flagging, the rule that unverifiable numbers always return REVIEW, empty-answer handling, and the exact return shape. It also discloses a limitation (phrase rules are a baseline only) that an agent needs in order to trust a SEND.

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 the one-line purpose, then verification scope, then return shape, then caveats. Dense but every sentence carries information; the description is fairly long and the Args block repeats what the schema already shows, costing a point.

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?

There is no output schema, and the description compensates by spelling out the returned JSON object (decision and flags with type/span/reason/source). Combined with the decision semantics (REVIEW vs SEND) and the precondition skill, an agent has everything needed to invoke 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 coverage is 0% and the schema is bare, so the description must carry the load — it documents both params as verbatim customer question and draft answer, and adds the semantic constraint that an empty answer yields REVIEW. It is missing any note on length/format constraints on the raw strings, so it is not a full 5.

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 first sentence names a specific verb (check), a specific resource (an AI-drafted answer to a US retirement-account question) and the workflow position (before it is sent to a customer). It enumerates the verification categories — contribution limits, RMDs, rollovers, early-distribution tax, excess contributions — so an agent can distinguish it from sibling data tools like get_facts and contribution_room.

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 gives clear situational context ('before it is sent to a customer') and names a downstream alternative workflow ('also run the advice-judge skill before treating SEND as final'), which is strong routing guidance. It does not explicitly state when not to use this tool versus the siblings (e.g., when you only need raw facts, use get_facts), so it stops short of the 5.

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

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, and the description adds real substance beyond them: it is deterministic, only tax year 2026 is supported, no Roth amount is returned without magi, and the response carries warnings/notes/not_covered that must be surfaced rather than backfilled. That is materially more than the safety hints provide.

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 purpose, then the determinism directive, then the return contract, then a parameter block. Every segment earns its place, though the Args list is long and a few entries (e.g. year, magi) restate in prose what could be tighter.

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 supplies the return shape (lines with label/amount/why/source, plus warnings, notes, not_covered), the version constraint, the magi dependency, and all ten parameter meanings. Nothing an agent needs to call this correctly is missing.

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 0%, so the description must carry the full burden and it does: age_at_year_end drives 50+ and 60-63 catch-ups, compensation caps the IRA limit, plan_type enumerates its accepted values, year is constrained to 2026, and lived_with_spouse is scoped to married_separate. It supplies semantics the bare schema cannot.

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 concrete verb ('compute') and resource ('contribution room this year') and enumerates the account types covered (401(k)/403(b)/TSP, SIMPLE IRA, traditional IRA, Roth IRA). It also signals its authoritative basis ('IRS-sourced limits'), so an agent can tell it apart from the generic siblings check_answer and get_facts without opening the 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?

Gives an explicit when-to-use directive: 'call this instead of stating contribution limits from memory, which are often last year's.' It also includes an explicit handling instruction for gaps ('Relay not_covered to the user rather than filling those gaps') and a scope exclusion ('Not tax or financial advice'), which is unusually complete routing guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully disclosed. The description adds behavioral context by stating the facts table includes source URLs and verification dates, which informs the agent of exactly what the response will contain. No contradiction exists.

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 description is a single paragraph that front-loads the core purpose ('Return the full IRS-sourced facts table'), then lists contents, then gives a use case, and ends with a redundant 'takes no arguments.' Every sentence serves a purpose, and the structure is efficient.

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?

Given the tool is parameterless and read-only, the description covers all essential aspects: what data is returned (contribution limits, RMD rules, rollover rules, early distribution tax/exceptions), additional metadata (source URL and verification date), and the intended use. No output schema exists, so the description is the primary documentation, and it is sufficient for an agent to select and invoke the tool correctly.

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?

The schema has zero parameters, so the baseline is 4. The description's note 'Takes no arguments' adds no new information but is consistent. Since there are no params, the description appropriately does not need to compensate for schema gaps.

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 states a specific verb 'return' and resource 'full IRS-sourced facts table the checker verifies against,' clearly distinguishing it from the sibling check_answer which presumably verifies answers. It also enumerates the specific content types, leaving no ambiguity about the tool's function.

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 gives explicit guidance on when to use it: 'Use it to show a reviewer why a number was flagged,' implying it is for retrieval and justification, not for verification itself. Since the only sibling is check_answer, the context makes the division of labor clear, though it does not explicitly state 'use check_answer for verification.'

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