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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context on top: the state rate in force on the given date, application of the federal floor, pre-tax basis, and exclusion of overtime and tips. It stops short of stating rounding behavior or what happens for states without their own minimum wage.

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?

Two sentences, front-loaded with the outputs and the inputs, then caveats. Every clause carries information an agent would otherwise have to guess; nothing is padded.

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 simple four-parameter read-only calculator with full schema coverage and no output schema, the description supplies the essential semantic contract (units, pre-tax basis, federal floor, exclusions) and names the three returned figures. Only edge-case behavior (invalid state, date outside the window) is left unaddressed, which is minor.

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 all four parameters (including the YYYY-MM-DD date range and the 2-letter-code/name state format) are fully documented in the schema. The description restates the 40/52 defaults already present in the schema and adds only the notion that the state rate is date-dependent, so the 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?

The description names a specific computation and its outputs: gross weekly, monthly and annual pay derived from a state's minimum wage, which cleanly separates it from get_minimum_wage (rate lookup) and compare_states (multi-state comparison). It never names those siblings explicitly, so the differentiation is inferred rather than stated.

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 implied by the output description (use this when you need dollar amounts rather than the raw rate), and the 2026-2027 window plus pre-tax/overtime/tips exclusions scope it usefully. However, there is no explicit 'use this instead of get_minimum_wage when...' routing statement, leaving the agent to infer the choice among the three siblings.

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?

The annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds useful behavioral context: the returned fields, sorting order, highest-lowest gap, and the full-time annual pay calculation.

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?

It is a single dense but well-structured sentence, front-loaded with the core comparison purpose and followed by return fields and scope limits. Every clause adds useful 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 must explain what comes back, and it does: standard rate, tipped cash wage, tip credit, effective date, annual pay, sorting, and the gap. It is complete for an agent to call and interpret the tool.

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 parameters are already well documented. The description reinforces the state-count limits and 2026-2027 date window, but does not add new syntax or format details beyond what the schema provides.

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 uses a specific comparative verb and resource: side-by-side minimum wages for 2 to 10 US states/DC on one date. It clearly distinguishes this multi-state comparison from the single-state get_minimum_wage sibling and from annual_income_at_minimum_wage.

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 usage constraints: 2 to 10 states, one date in 2026-2027, and state-level only. It does not explicitly name the sibling alternatives or state when-not to use this tool, which keeps it from a 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 establish readOnly/idempotent/non-destructive, but the description adds substantial behavioral context beyond them: data provenance and check dates (DOL July 2026 tables, state pages checked October 2026), inclusion of post-training-data increases, the $7.25 federal floor being applied and disclosed, and a policy of reporting unpublished indexed rates as 'not announced' rather than estimating. That is exactly the kind of trust-relevant disclosure an agent needs when citing figures.

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 and output fields, then provenance and caveats, which is the right ordering. Every sentence carries information, though the phrasing is dense and a couple of clauses (e.g., the training-data remark) could be tightened without losing meaning.

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?

No output schema exists, and the description compensates by enumerating the returned fields and explaining the edge-case return ('not announced' for unpublished indexed rates). Combined with the stated date range, state-level scope, and federal-floor behavior, an agent has everything needed to call and interpret it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: that 'date' is the point on which the rate is in effect (not a lookup-publication date), and that state input is limited to a single US state or DC with the federal floor applied where no state law exists. It does not add syntax hints, which the schema already covers.

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+resource (minimum wage for one US state or DC on a given date) and enumerates the returned fields (standard hourly rate, tipped cash wage, tip credit, effective date). The explicit 'state-level only: city and county rates are not included' cleanly separates it from a broader or comparative sibling like compare_states.

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 clear context for when this applies: a single state on a date in 2026-2027, with an explicit exclusion for sub-state rates and a stated fallback behavior for missing/lower state law. It does not explicitly name which sibling to use instead for cross-state comparison or historical/upcoming-increase lookups, so it stops short of a full when/when-not/alternatives map.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value is in the extra behavior it discloses: results are date-sorted, include enacted and inflation-indexed 2027-01-01 changes, and mark unpublished indexed changes as announced:false. That announced:false nuance is genuinely useful for an agent reasoning about missing numbers; only pagination/volume behavior is unaddressed.

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?

Two dense sentences with the scope and window front-loaded and no filler. The second sentence is clause-heavy ('already enacted in law or announced under inflation indexing') but each clause carries real behavioral meaning, so nothing is wasted.

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 return-value burden and does so fully: new rate, previous rate, change, tipped cash wage, sort order, and the announced:false edge case. Combined with complete parameter coverage, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3. The description restates the 'from' default and the optional state filter but adds nothing about the schema's exclusive boundary on 'from' or the accepted state name/code formats, which remain schema-only details.

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 ('Every scheduled state minimum wage change'), plus the exact temporal window (from a date through 2027-12-31), the sort order, and the returned fields. An agent can distinguish this forward-looking schedule tool from get_minimum_wage or compare_states 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?

The temporal scope and the 'default today' behavior imply when the tool is appropriate, and the optional states filter is noted. However, it never names an alternative or states an exclusion, so the boundary with get_minimum_wage (presumably current rates) is left to inference.

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