pound.one

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the constraint that 'now' refers to the latest stored observation, not a live price, and notes the coverage ranges for RPI and CPI, which is useful behavioral context. It doesn't mention rounding behavior explicitly (though the schema does), nor does it describe output format, but with annotations carrying the safety burden, this is adequate.

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 with no waste, front-loading the core purpose. The second sentence packs useful constraints about series and 'now'. Efficient and structured.

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 calculation tool with full schema coverage and annotations, the description is mostly complete. It covers series coverage and 'now' semantics, but doesn't mention output format (no output schema exists) or potential limitations like data availability beyond 2026. Adequate but could be more complete.

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 schema already documents all parameters thoroughly. The description adds some meaning by explaining the 'now' value and series coverage, but largely repeats what the schema provides. Baseline 3 is appropriate when schema does the heavy lifting.

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 (compare) and resource (GBP purchasing power between years). The title reinforces the verb+resource. It doesn't explicitly differentiate from siblings like calculate_take_home or compare_public_spending, but the purpose is clear enough.

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?

Provides important context about series coverage (RPI from 1948, CPI from 1988) and clarifies what 'now' means, which helps an agent choose the right series. However, it does not explicitly say when to use this tool versus the sibling tools, leaving some inference to the agent.

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 a read-only, idempotent, closed-world pure calculation, and the description is consistent with them. It adds real behavioral context beyond the annotations: the tax year, the excluded income components, the jurisdiction gap, and the fact that a taxpayer income rank is included in the result.

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 compact sentences, no filler: capability first, then scope limits, then exclusions and the extra return value. Every clause carries information an agent needs.

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 does note that a historical income rank is returned, but it does not describe the main figures returned (net pay, tax and NI breakdown) or currency assumptions beyond GBP in the schema. For a read-only calculator this is close to complete, with a minor gap on the return payload.

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 67%, and the one undocumented parameter, mode, has no description in the schema at all. The description compensates by spelling out the two semantic directions (tax from a salary vs. salary needed for a target net), which is exactly the ambiguity mode resolves.

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 computation (employee income tax and National Insurance for 2026/27) and names both directions it supports: gross-to-net and net-to-gross. Sibling tools (adjust_for_inflation, compare_public_spending) are unrelated calculations, so no differentiation is needed.

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?

Explicit geographic applicability ('England, Wales and Northern Ireland only; Scotland is unsupported') and explicit exclusions (pensions, student loans, benefits) tell the agent when this tool is valid and what it will not model. It does not name alternatives or when-not-to-use cases, but none of the siblings compete with it.

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 readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real context beyond that: the NHS figure is a DHSC day-to-day proxy and the values are 'illustrative averages, not live spending rates' – a caveat that materially affects how an agent should present results.

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 sentences, front-loaded with the core action, and the two caveats that follow are non-redundant since one explains a proxy choice and the other guards against misinterpretation as live data. Slightly more prose than strictly needed but nothing 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 compensates by naming the return shape (share, duration, comparisons against other budgets) and warning that values are illustrative averages. For a 2-param read-only calculator this is close to sufficient, though it doesn't state the output units or timeframe of the 'duration' figure.

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 both parameters (amount in GBP, budget enum with default 'nhs') are fully documented by the schema. The description adds only that the response 'also includes other budgets', which is output behavior rather than parameter meaning. 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?

States a specific verb ('Express a GBP amount') and resource ('2025-26 public budget') plus the output form ('share and duration'). The 'comparisons against other budgets' clause distinguishes it from adjust_for_inflation and calculate_take_home, which do different arithmetic on amounts.

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 makes the use case inferable (converting a GBP figure into budget-relative terms) but never states when to pick this over adjust_for_inflation or calculate_take_home, nor any prerequisite. Usage is implied rather than guided.

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