Deadline Desk

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that ddr_ IDs produce signed v1 TRACE records while dd- IDs produce v0 log entries, but it does not explain invalid-ID behavior, error modes, or whether authentication is ever required for 'public' receipts.

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, no filler. The core action and source are front-loaded, and the second sentence efficiently explains the ID-prefix behavior.

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 single-parameter getter with no output schema, the description covers the essential behavior and the ID-format distinction. The remaining gaps, such as invalid-ID handling and explicit relationship to lookup_policy, are minor but real.

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 only types receipt_id as a string. The description compensates meaningfully by defining two ID families and the different output formats tied to them, which is real semantic value beyond the schema.

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 verb and resource ("Fetch a public receipt") and scopes it to receipts from a prior Deadline Desk policy lookup. It also distinguishes receipt-ID families and their return formats. It does not explicitly contrast with the sibling lookup_policy, keeping it from 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?

Usage is implied by "from a prior Deadline Desk policy lookup" and by the two ID-prefix cases, but there is no explicit guidance on when to use this versus lookup_policy or what to do for other receipt sources. An agent can infer context but is not routed between alternatives.

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?

With no annotations, the description carries the burden and does disclose real behavior: responses include quoted source text, a TRACE receipt, provenance badges (live|curated|archive), and an ordering rule where exceptions surface before headline January dates. It stops short of stating error behavior for unknown stores or whether fetching is live or cached.

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 purpose in the first sentence, and the seasonal triggers follow in compact, information-dense clauses. Some internal jargon ('price_adjustment_detail honesty', 'TRACE receipt') is cryptic and costs a bit of clarity per word.

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 four-parameter, no-annotation lookup tool with no output schema, the description covers scope (US retailers only), the returned artifacts (quoted source text, receipt, provenance badges), and the ordering of exceptions — enough to call it correctly without guessing.

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 75%, so the schema already explains store, as_of, and anchor_date, and the description adds nothing param-specific. The mentions of 'holiday_extended_return.policy_year' and 'price_adjustment_detail' are output field names, not parameter semantics, so 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 (look up) and a tightly scoped resource: a US retailer's published return, price_adjustment, warranty, or cancellation policy, plus the shape of the answer (quoted source text, TRACE receipt). It never names the sibling get_receipt, and the phrase 'TRACE receipt' could even blur the line with it, so sibling differentiation is left implicit.

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 concrete calling triggers — before Black Friday / Cyber Week purchase decisions, and during the Dec 26–Jan 31 return window for deadline urgency. That is clear when-to-use context, but there is no when-not guidance and no explicit alternative tool to consult instead.

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