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

Annotations already indicate this is a non-read-only, non-destructive write. The description adds data-quality expectations ('Do not invent terms', 'Extracted fields need confirmation'), which is useful behavioral context beyond the annotations. But it doesn't clarify what happens if fields are unconfirmed or what 'reviewed' entails.

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 very short and front-loads the purpose before the cautions. It contains no filler, though the fragmentary style leaves some ambiguity that a slightly fuller sentence could resolve.

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 complex write tool with a nested purchase object and zero schema description coverage, the description is far too sparse. It omits required-field guidance, how confirmation should be represented, and how it differs from update_purchase. Output schema and annotations cover some ground, but not enough to compensate.

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 0% and the description provides no parameter-level semantics. It mentions 'terms' and 'fields' only generically, so an agent receives no help understanding the nested purchase object or its many fields.

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 says 'Save a reviewed purchase', which states a verb and resource. However, 'save' is ambiguous between create and update, and the sibling update_purchase exists, so it does not clearly distinguish the operation. The qualifier 'reviewed' is also unexplained.

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 implies usage by saying 'Do not invent terms' and 'Extracted fields need confirmation', which suggests the tool should only be called with confirmed data. It does not name alternatives like update_purchase or explain when-not-to-use, leaving the guidance implicit.

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=true, openWorldHint=false and destructiveHint=false, so safety is partly covered. The description adds genuinely useful context against a name that sounds like a write operation: "Never sends it" tells the agent this only produces a draft and no request is transmitted. It still doesn't say whether the draft is persisted or only returned, so it falls short of 5.

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 short sentences with zero filler; the action is front-loaded and the critical non-sending constraint is stated up front rather than buried.

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?

An output schema exists, so return values need not be described, and the annotations plus the "never sends" note cover the safety profile. Still missing for a drafting tool: whether the draft is saved, what "confirmed fields" means, and any per-parameter meaning, leaving the definition minimally adequate rather than 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 0%, so the description must carry the burden for three parameters. It names the four kinds, which loosely maps to the `kind` enum, but says nothing about `reason` or `purchase_id` beyond the ambiguous phrase "confirmed fields" — that gap is what the purchase_id refers to is never made explicit.

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?

Specific verb ("Draft") plus a concrete resource set (return, refund, warranty, replacement request), which no sibling tool covers. However it does not explicitly differentiate itself from siblings like get_warranty_status or update_purchase_status, and "from confirmed fields" is left undefined.

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 gives no when-to-use guidance, no prerequisites (e.g. a purchase_id must already exist, likely from get_purchase_details), and names no alternatives. The only usage-adjacent statement is "from confirmed fields," which implies but never states that input data must already be validated.

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=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds only that results are paginated, which is modest but useful context beyond the annotations.

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?

A single short sentence that is front-loaded with the verb and resource. Nothing is wasted, though 'actual local' is slightly puzzling phrasing.

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?

An output schema exists so return values need not be described, but for an 8-parameter filtered search with zero schema documentation, the description omits which filters exist and how paging behaves. That is a significant gap for an agent trying to invoke 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 description coverage is 0% across 8 parameters, so the description must carry the load, yet it only says 'filters and pagination' generically. It never mentions the status enum values, date_from/date_to, category, merchant, or search, leaving the agent to guess what can actually be filtered.

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 clear verb (Search) and resource (local purchases), and 'with filters and pagination' signals it is a list/browse operation, which implicitly distinguishes it from get_purchase_details. However, it does not name any sibling or explain the odd 'actual local' qualifier.

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?

No guidance on when to use this versus get_purchase_details, get_warranty_status, or get_upcoming_deadlines. The agent must infer that this is the general listing tool from the name alone.

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=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds that deadlines are classified as confirmed/tentative/unknown, a useful data-confidence trait, but says nothing about permissions or behavior on a missing/invalid ID.

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?

One front-loaded sentence with no filler; the enumerated outputs are dense but each item earns its place. Slightly list-heavy for a single sentence, but efficient.

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 an output schema present, return values need not be explained, and annotations carry the safety profile. The description covers purpose and content well; the only real gap is the undocumented purchase_id semantics.

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 purchase_id parameter has 0% schema description coverage, and the description does not explain its format, source, or expected values. Beyond implying that the ID selects the purchase to fetch, it adds nothing to 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?

States a specific verb (Get) plus resource (purchase) and enumerates the returned facets (document metadata, policy evidence, deadlines). It reads clearly against the list-style sibling get_my_purchases, though it never names a sibling to differentiate explicitly.

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?

No when-to-use guidance and no mention of alternatives such as get_my_purchases or get_warranty_status. The intended usage (fetch details for one known purchase) is only implied by the required purchase_id.

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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results are filtered to 'confirmed' and 'actionable' deadlines and evaluated per purchase's timezone. It stops short of explaining how 'actionable' is determined or any rate/limit 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?

One tight sentence with no filler, and the core action is front-loaded. The trailing timezone clause is slightly compressed and could read ambiguously, but 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?

An output schema exists, so return values need not be described, and annotations cover safety. Still, for a tool whose central term is 'actionable confirmed', the description leaves that qualifier undefined and gives no routing guidance against the seven sibling tools.

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% — the single 'days' parameter has only default/min/max and no prose. The description partially compensates by tying the window to 'within N days', but it never clarifies whether the window is calendar days from now, how the upper bound (3650) behaves, or what happens at days=0.

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 verb+resource ('Get ... deadlines') and adds scoping qualifiers ('actionable confirmed', 'within N days', 'in each purchase's timezone') that separate it from warranty or return-request siblings. It is clear what is retrieved, though it never explicitly contrasts itself with the other deadline-adjacent 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?

Usage is only implied by the phrase 'actionable confirmed deadlines'; there is no explicit statement of when to call this versus get_warranty_status or generate_return_request, and no prerequisites or exclusions are given.

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=true and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral note — that unknown starting dates or terms remain unknown rather than being inferred — which is more than the annotations provide, but it still says nothing about auth, rate limits, or how missing data is surfaced.

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 tight sentences with no filler, and the primary purpose is front-loaded before the caveat about unknown data.

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?

An output schema exists, so return values needn't be documented, and read-only annotations cover the safety profile. For a single-param read tool the description is nearly sufficient, with only the purchase_id semantics left unaddressed.

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 0%, so the single purchase_id parameter is undocumented in both schema and description. The description compensates only indirectly: it implies a purchase-scoped lookup but never explains the identifier's format or source, leaving a gap given the zero coverage.

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 (Get) and resource (warranty provider, terms, evidence, status), which is clear and distinguishable from generic siblings like get_purchase_details by naming warranty-specific fields. It does not, however, explicitly contrast itself with the nearby get_purchase_details or get_my_purchases tools, so it stops short of full sibling differentiation.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternative tools such as get_purchase_details. The agent must infer from the name alone that this retrieves warranty data for a specific purchase.

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 state readOnlyHint=false and destructiveHint=false, so the agent knows this is a non-destructive write. The description adds a crucial behavioral warning: it replaces fields, so data can be lost if not preserved, which is valuable context beyond the annotations. No auth or rate-limit details are provided, but the core risk is communicated.

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 concise imperative sentences, front-loaded with the action and immediately followed by the prerequisite. No wasted words.

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 tool with a complex nested input schema and 0% parameter coverage, the description is insufficient. It omits any explanation of the purchase object structure, the purchase_id, or the meaning of the nested policies and field statuses. While it covers the high-level replacement behavior, it leaves too much unsaid for an agent to invoke correctly without inspecting the schema in detail.

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?

With schema description coverage at 0%, the description must compensate, but it doesn't describe the 2 parameters (purchase_id and the nested purchase object). The baseline for 0 params is 4, but here we have 2 parameters (one nested) with no semantic explanation beyond the schema's own title. The schema's structure (additionalProperties=false, required product_name) is complex, and the description doesn't add meaning. However, the 'preserve fields' hint implies full replacement semantics for the purchase object.

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 verb 'Replace' and resource (fields/policies) make the update operation clear. However, it doesn't differentiate from update_purchase_status, which likely updates only the purchase status, leaving the boundary between the two update operations somewhat ambiguous.

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 second sentence 'Retrieve details first to preserve fields' gives a clear prerequisite and implies that fields not included will be lost. It doesn't explicitly mention when to prefer update_purchase_status over this tool, but the overall context is strong.

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 this is a non-readonly, non-destructive, closed-world mutation, so safety is covered. The description does add meaningful nuance that the recorded status is user-asserted rather than merchant-verified, but it omits side effects, idempotency, and whether recording e.g. 'returned' or 'refunded' triggers downstream activity.

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 short, front-loaded sentences with no filler; the caveat follows the action statement. It is efficient, though the brevity edges toward under-specification rather than true conciseness.

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?

An output schema exists so return values need not be described, and annotations cover the safety profile. Still, for a mutation exposed alongside update_purchase and warranty/return siblings, the description omits state-transition rules and cross-tool relationships an agent needs to call 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 description coverage is 0%, so the description must compensate for parameter meaning, and it says nothing about either purchase_id or status. The enum values in the schema are somewhat self-documenting, but no transitions or valid-status semantics are explained anywhere.

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 verb+resource pair is inferable from the name and the description's 'Record a user-reported status', and the 'user-reported' qualifier hints at trust level. However, the description never states it modifies a purchase record nor distinguishes itself from the sibling 'update_purchase', leaving an agent to infer scope from the tool name alone.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the closely related siblings (update_purchase, generate_return_request, get_warranty_status). The caveat 'This does not confirm any merchant approval' is a scoping remark, not routing guidance.

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