Odometry Mileage Log

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 covered. The description adds genuinely new behavioral detail beyond that: the exact rate table by period and category, the July 1, 2026 rate-change splitting behavior, and the fact that a custom rate is shown alongside the IRS amount rather than replacing it. For a computation tool with an output schema, this is meaningful extra context.

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 trigger condition and routing exclusions are front-loaded in the first and last sentences, with operational detail in between. It is dense with parentheticals and enumerated rates, which is justified by the domain but makes it heavier than a two-sentence ideal, so not a 5.

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 an 8-parameter, all-optional computation tool with an output schema, the description covers trigger conditions, rate values by period and category, odometer conversion, segment splitting, and rate comparison, plus explicit exclusions. Nothing an agent needs to call it correctly is missing, and return values are left to the output schema.

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% with defaults and examples, so the schema carries the parameter burden and baseline is 3. The description goes further by explaining the semantics of the date field (picks the rate for that date), the either/or relationship between miles and odometer fields, and the split-across-rate-change purpose of segments, adding real meaning beyond field descriptions.

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 and spells out the distinct computations it performs: applying the IRS rate by date, splitting miles across the July 2026 rate change, comparing a custom employer rate, and converting odometer readings to miles. It also explicitly names what it is not, routing trip logging to the sibling generate_mileage_log, so an agent can differentiate 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?

Opens with an explicit trigger phrase ('use this when the user asks...') and backs it with three realistic paraphrase examples covering deduction, employer rate, and odometer inputs. It also names the alternatives and exclusions ('does not build a trip-by-trip log (use generate_mileage_log), look up distances, or give tax advice'), leaving nothing to inference.

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 only cover read-only/idempotent/non-destructive, so the description goes well beyond them: it discloses the IRS rate schedule applied per trip date (70c 2025, 72.5c Jan-Jun 2026, 76c Jul-Dec 2026), odometer continuity checks, commuting and missing-purpose flagging, monthly/purpose/client totals, and the two output artifacts. It also states boundaries (no distance lookup, no GPS, no tax advice), which is exactly the context annotations cannot convey.

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 'Use this when' trigger list, then inputs, then processing behavior, then outputs, then exclusions — good ordering. The synonym-heavy trigger list is long but functional for routing; a few phrasings ('mileage log', 'mileage log template', 'printable mileage log') are borderline redundant.

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 12-parameter tool with nested objects and an output schema, the description covers what inputs are accepted, what processing occurs, what is returned, and what is out of scope. Nothing an agent needs to decide or call correctly is missing, and return-value detail is appropriately left to the output schema.

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 baseline is 3; the description earns above baseline by explaining how the parameter families combine (typed trips + recurring occurrences + attached CSV/XLSX) and by naming the custom employer rate as an alternative to the IRS rate. It does not restate per-field syntax, which the schema already handles thoroughly.

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 precise verb+resource and enumerates the concrete deliverables (PDF mileage log, XLSX file) produced from typed trips, recurring trips, or an attached spreadsheet. It explicitly names the sibling tool calculate_mileage_reimbursement as the wrong fit for a single quick total, so an agent can distinguish the two without opening either 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?

It gives explicit trigger utterances ("turn these trips into a mileage log for my taxes", "reconstruct my mileage log from my calendar") plus an explicit when-not ("Do not use for a single quick mileage total with no trip list (use calculate_mileage_reimbursement)"). It also enumerates out-of-scope capabilities (distance lookup, GPS tracking, tax advice).

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