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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotent. The description adds material context beyond them: the authorization constraint ('Managers only'), the scope constraint ('assigned to the caller'), and a required confirmation step before committing an irreversible decision. It does not spell out that the decision is final/irreversible or the effect of the optional comment, so it is useful but not exhaustive.

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 compact sentence pair with no waste; the authorization constraint and confirmation requirement are front-loaded and actionable.

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 destructive, single-target mutation with an output schema already present, the description covers actor, scope, and the confirmation safeguard. It is nearly complete, missing only parameter meaning and any note on reversibility, which the destructiveHint partly signals.

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 carries the full burden of explaining the three parameters, yet it mentions none of them. 'report_id' and the 'decision' enum are largely self-describing, but the 'comment' parameter (default '', maxLength 500) has no semantics offered anywhere about what it is for or whether it is required for rejection.

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 pair (approve/reject) and resource (a report assigned to the caller), which is clearly distinguishable from sibling tools like submit_for_approval and list_pending_approvals. An agent can identify the action 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?

Provides clear context: restricted to managers, applies only to reports assigned to the caller, and requires user confirmation first. It stops short of naming when NOT to use it or pointing to alternatives (e.g., list_pending_approvals to find a report_id), so it is strong but not complete.

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 non-destructive, non-readonly, non-idempotent write semantics. The description adds meaningful context the annotations do not: the result is a DRAFT that is not submitted, and it includes a compliance check. This is exactly the kind of write-side clarification that helps. Not a 5 because it does not mention persistence/visibility of the draft or whether it can be edited/regenerated afterward.

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 front-loads the action ('Create a DRAFT'), then states the return ('return it with a compliance check'), then the crucial non-effect ('Nothing is submitted'). 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?

Output schema exists, so return-value details needn't be spelled out, and annotations cover the safety profile. The description covers the essential non-obvious behavior (draft-only, compliance check). A small gap remains around lifecycle — what happens to the draft afterward, and whether re-calling duplicates it (idempotentHint=false).

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%; the schema already documents 'month' (default = current month) and 'txn_ids' (omit to include all). The description adds nothing about parameters, so it merely repeats the tool purpose. Baseline 3 given moderate schema coverage with the key semantics documented in 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?

Specific verb (Create) + resource (draft expense report) + scope ('Nothing is submitted') clearly distinguishes it from the submit_for_approval sibling. 'DRAFT' and 'return it with a compliance check' tell an agent exactly what this does versus the other approval-related tools in the list.

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 phrase 'Nothing is submitted' implicitly routes the agent here when draft-only behavior is needed, versus submit_for_approval. But no explicit 'use X instead when ready to submit' statement is provided, so an agent must infer the boundary from the sibling name.

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 openWorldHint=false, so the safe-read profile is covered. The description contributes one useful behavioral fact — results are scoped to the caller's own transactions — but says nothing about result volume, whether it spans card and out-of-pocket activity, or how incomplete data is handled.

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 tight sentence with the audience ("caller's transactions") front-loaded and the filtering condition following immediately. Nothing is wasted and nothing is 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 lone parameter is fully documented in the schema. The description covers what is found and for whom; only the meaning of the domain-specific "entertainment attendee lists" and edge-case behavior remain unexplained.

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 a single parameter at 100% schema description coverage, the schema already documents the YYYY-MM format and the current-month default. The description adds no extra semantics about the month filter, so the 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?

The description names a specific verb ("Find") and resource ("the caller's transactions") plus the exact filter condition (missing receipt images or entertainment attendee lists). This clearly separates it from list_card_transactions and validate_tax_compliance, though it never names a sibling explicitly as the scoring rubric's top tier asks.

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 explicit when-to-use statement, no prerequisites, and no named alternative. The use case (preparing an expense report, satisfying receipt requirements) is only implied by the description's filter condition, leaving the agent to infer routing.

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 openWorldHint=false, so the safety profile is clear without the description. The description adds the fact that it returns all of the caller's cards with three computed figures, but says nothing about card count, pagination, or whether the month affects the spend calculations. No contradiction with 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?

One sentence, front-loaded with the verb and resource, with the returned fields listed last. No filler and 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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile; the one optional parameter is documented in the schema. The definition is adequate for a simple read tool, though it omits any 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 description coverage is 100% and the single 'month' parameter is fully documented in the schema, including the YYYY-MM format and current-month default. The description never mentions the month parameter, so it adds no meaning beyond the schema — the baseline 3 for high coverage 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?

States a specific verb (Show) and resource (caller's corporate cards) plus the exact fields returned — monthly limit, amount spent, remaining balance — which separates it conceptually from the transaction-listing and approval siblings. However, it does not name or reference any sibling tool, so the differentiation is implicit rather than explicit.

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 explicit when-to-use statement, no prerequisites, and no mention of alternatives such as list_card_transactions. Usage is only inferable from the described return fields (a balance check), which meets the 'implied usage' bar but leaves the agent to guess.

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 openWorldHint=false, so the safety profile is covered. The description adds the useful constraint that results are limited to the caller's own card transactions (an auth-scoping detail beyond the annotations), but says nothing about pagination, result volume, or ordering.

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 front-loaded sentence with no filler; the scope (caller, card transactions, monthly window) is stated immediately.

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 no explanation, and both parameters are documented in the schema. However, for a listing tool the description omits any mention of result size, pagination, or ordering, which are exactly the gaps a list tool should close.

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% – both month (YYYY-MM, defaults to current month) and card_id (omit for all cards) are fully documented in the schema. The description's 'for a month' and 'caller's' phrasing mirrors rather than extends that, 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 (list) and resource (corporate card transactions) with the caller scope and month granularity. It does not distinguish itself from siblings like get_card_balance or find_missing_receipts, but the resource is unambiguous.

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, no mention of alternatives, no exclusions. The 'for a month' phrasing implies a per-month query window but tells the agent nothing about when this tool is preferable to its siblings.

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 openWorldHint=false, so the safety profile is covered. The description adds non-redundant context: an authorization constraint (managers only) and the fact that results are scoped to the caller's own approval queue, which the annotations do not 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?

A single front-loaded sentence with the access gate and the result scope, zero filler. Every clause earns its place.

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 no explanation, and the description covers the access constraint and result scope. Adequate for a no-param read tool, though it could note what happens when the caller has no approvals pending.

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 tool takes zero parameters, so the baseline is 4. There is nothing for the description to clarify beyond what the empty schema already shows.

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 ('list expense reports') plus a precise scope ('waiting for the caller's approval'), which separates it from siblings like decide_approval and submit_for_approval. It stops short of explicitly naming the alternative tools, but the resource is unambiguous.

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 'Managers only' gate and 'caller's approval' scope give real context for when to call it, but no explicit when-not condition or named alternative (e.g. use decide_approval to act on these items) is provided. Usage is implied rather than spelled out.

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 non-read-only, non-idempotent, and non-destructive. The description adds important behavioral context beyond annotations: a refusal condition and a user-confirmation requirement. It omits what happens after submission or reversibility, but the added value is real.

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 core purpose and then the critical usage constraints. Every sentence earns its place with no filler.

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?

Given an output schema exists and annotations cover the safety profile, the description provides adequate context for a mutation tool. It lacks parameter details and next-step guidance, but the critical safety constraints are present.

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 single required parameter report_id has no description. The description only implies it must be a caller-owned draft report, with no format or sourcing guidance. This is minimally adequate for a required parameter.

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 ('Submit') and resource ('draft reports to their manager'), clearly distinct from siblings like draft_expense_report or decide_approval. The approval workflow aspect is implied rather than stated, but the core purpose is unambiguous.

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?

States an explicit prerequisite ('Only call this after the user has explicitly confirmed submission') and a refusal condition ('Refused if compliance blockers remain'). No alternatives are named, but the when-to-use context is clear.

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 openWorldHint=false, so the safety profile is covered. The description adds useful scope context by naming the rule categories checked and disclosing that it also estimates deductible input VAT, but says nothing about batching behavior, failure modes, or performance limits.

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 dense sentence with no filler, front-loaded on the core action and immediately qualified by the rule set. Every clause carries information.

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 annotations covering the safety profile and an output schema covering return values, the description only needs to convey what is checked and roughly what comes back, which it does. Minor gap: it does not indicate the scope of validation (per-transaction results, aggregate, or both).

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?

There is a single parameter (txn_ids) with 100% schema description coverage, so the schema already explains it. The description adds no format or scoping detail (e.g., max number of ids, mixed-vendor ids), so the baseline of 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?

The description gives a concrete verb ('Check') and resource ('transactions') and enumerates the specific rule families it applies (receipts, clean-card merchants, entertainment evidence, late-night/weekend use), plus a second function (estimating deductible input VAT). This is far more specific than the name alone. It does not explicitly differentiate from the overlapping sibling find_missing_receipts, which is the only thing 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 rather than stated: an agent can infer this is the compliance/validation step, but there is no guidance on when to call it versus find_missing_receipts or list_card_transactions, and no stated prerequisites. The closest sibling (find_missing_receipts) overlaps on the 'receipts' dimension and is never mentioned.

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