Corporate Gift Picks

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context beyond annotations by stating the returned values and that the calculation matches the Corporate Gift Picks budget tool, with no contradiction.

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 three efficient sentences: usage condition first, return values second, and a brief contextual note third. Every sentence contributes and 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?

For a simple read-only calculator with complete parameter descriptions and no output schema, the description adequately explains inputs, outputs, and usage. It could be slightly more complete by defining how price bands are determined or the exact return format, but it is sufficient to 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?

Schema coverage is 100%, so the schema already documents headcount, amount, and amount_type thoroughly. The description restates the total versus per-person distinction but adds no syntax or constraint details beyond the schema, making the baseline 3 appropriate.

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 calculation: it takes headcount and an amount type to return per-person and total amounts, a matching price band, and a guide link. It does not explicitly distinguish this from siblings such as find_gift_picks or list_gift_guides, so it falls short of a 5.

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 a clear usage condition: use when someone has a headcount and either a total or per-person amount and wants to know what each person gets. It does not provide when-not conditions or name alternative tools, 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 that this is a safe, read-only, idempotent lookup. The description adds useful behavioral context by specifying that it returns up to 5 picks from guides and shows price bands rather than current prices. It does not cover pagination or failure behavior, but for this read-only tool that is a minor gap.

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 three compact sentences, front-loads the usage condition, then explains the return shape and the price-band caveat. Every sentence contributes information an agent needs to select or interpret the tool.

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?

Because there is no output schema, the description appropriately explains the returned fields and the fact that results use price bands rather than live prices. Combined with complete parameter documentation and read-only annotations, it gives enough context to invoke and interpret 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?

Schema description coverage is 100%, so the input schema already documents budget_band, recipient, and limit thoroughly. The description reinforces budget and recipient filtering and the five-pick cap, but adds little parameter syntax or meaning beyond the schema itself.

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 and resource: finding gift picks for a budget and recipient. It also clarifies that results come from Corporate Gift Picks guides and include item name, price band, reason, and guide link. It does not explicitly distinguish itself from list_gift_guides or estimate_gift_budget, so it stops short of a 5.

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 a clear usage trigger: use when someone wants gift ideas for a given budget and recipient, with recipient examples. It does not explicitly state when to choose estimate_gift_budget or list_gift_guides instead, so the alternative-routing guidance is incomplete.

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 mark it read-only, idempotent, non-destructive, and not open-world; beyond that, the description discloses data provenance (USPS source and last-checked date), geographic scope, and the carrier-published-not-guaranteed caveat. It also states that UPS/FedEx schedules are not covered.

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 front-loads the use case and follows with output scope, disclaimer, and carrier exclusion in a compact sequence. The quoted result note is long but operationally relevant for setting expectations, and no sentence 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?

For a low-complexity, read-only lookup with full schema coverage and rich annotations, the description supplies the remaining needed context: year, geography, result contents, provenance, and carrier limitations. No output schema exists, but the description explains what results include.

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 single optional service parameter is fully documented in the schema at 100% coverage, including enum values and omission behavior. The description adds only 'by mail service' and does not add enum semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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 the resource (USPS holiday ship-by dates), the year, geography (lower 48), and the motivating question (last Christmas shipping day or days left). This is specific enough for an agent to distinguish it from sibling gift-budget, gift-pick, and gift-guide tools.

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 an explicit triggering user question and also scopes out non-USPS carriers by directing UPS/FedEx route questions to the carrier's own schedule. No sibling alternative is needed because the other tools handle different gift-planning tasks.

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, idempotentHint and a closed-world, non-destructive read, so the safety profile needs no restating. The description adds valuable behavior the annotations don't cover: what each returned item contains (title, one-line summary, link), which matters since there is no output schema.

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 usage trigger and followed by the return shape, with no filler. The parenthetical topic examples are slightly verbose but earn their place by disambiguating the topic enum.

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 three-optional-filter read tool with no output schema, the description supplies the missing piece: what each guide entry looks like. Only the unfiltered case (does it return all guides?) and any result-size limits are left unaddressed, which are minor for a read-only listing.

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% with three fully-enumerated filters, so the schema does the heavy lifting and the baseline is 3. The description only restates the three axes ('recipient, budget or topic') and adds illustrative examples ('gift cards', 'Christmas gifts for employees') that map onto existing enum values rather than adding new semantics such as default behavior when no filter is supplied.

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 and resource ('Returns guides by recipient, budget or topic') and clarifies the scope is editorial guides rather than individual picks. It implicitly separates itself from find_gift_picks and estimate_gift_budget through the guide/read framing, though it never names those siblings.

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?

'Use when someone wants to read a full guide or see what Corporate Gift Picks covers' is an explicit trigger condition tied to user intent. It stops short of naming alternatives or stating when NOT to use it (e.g. use find_gift_picks for a single product), so it is clear but not exhaustive.

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