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

With no annotations, the description carries the full burden and does disclose the key behavioral trait: the call may return before an answer exists and must be re-invoked with the event_id, i.e. it is asynchronous rather than blocking indefinitely. It also says where the human answers (dashboard or phone). It omits timeout/duration behavior, whether re-asking with question is allowed, and what a returned answer looks like, so not a 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?

Three tight sentences, front-loaded with the action and motivation before the mechanics. The parentheticals ("which environment, which customer, is this safe") earn their place by making the trigger concrete. Minor informal tone costs it the top score.

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 no output schema and no annotations, the description does most of the needed work: it explains the async wait/poll cycle, where the human replies, and the escalation intent. What is still missing is the shape of a successful return (answer text vs. a status plus event_id) and any guidance on how long to wait before re-calling.

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 both parameters are already documented in the schema, and the description largely restates them (event_id for continuing a prior question). The extra framing about event_id being "the event_id you were given" reinforces the polling loop but adds no new syntax or constraints. Baseline 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?

States a specific verb and resource ("Ask a person on your team a question and wait for their answer") plus the motivation behind it, so an agent knows this is a human-in-the-loop escalation rather than a data lookup. It does not explicitly differentiate itself from the nearest siblings (acme_check_approval, acme_recent_decisions), 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?

Gives clear trigger context with concrete examples of the ambiguity it resolves ("which environment, which customer, is this safe") and explicit polling guidance ("If the answer isn't there yet, call this again with the event_id you were given"). No explicit when-not-to-use or named alternatives against acme_check_approval, which keeps it at 4.

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?

No annotations are provided, so the description carries the full burden. It does disclose the branching behavior (executes on approval, reports on rejection, keeps waiting otherwise), which is valuable. However, it omits who/what grants approval, whether the call is idempotent, side effects of execution, and rate/timeout behavior for the 'waiting longer' path.

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 that front-loads the action and parenthetical state. Slight awkwardness ('a acme call') but no wasted content.

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 one-parameter mutation-adjacent tool with no annotations and no output schema, the description covers the outcome branches but leaves the meaning of event_id and the approval mechanism unexplained. It is adequate but has clear gaps.

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% for the single required parameter 'event_id', and the description says nothing about what an event_id is, where to obtain it, or its format. With low coverage the description should compensate but does not.

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 action on a specific resource: resolving a held 'acme' call that is waiting for human approval, with three possible outcomes (run if approved, report if rejected, keep waiting). This is far more than a restatement of the name. It doesn't explicitly compare against siblings, but the 'finish a held call' framing is clear enough to distinguish it.

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 ('WAITING FOR HUMAN APPROVAL') but never gives an explicit when-to-use or when-not-to-use statement, nor names acme_recent_decisions or any alternative. An agent can infer that it is for pending approvals, but the routing logic is left 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?

With no annotations, the description carries the full behavioral burden. It usefully discloses the shape of the content (approved/rejected, by whom, notes), implying a read-only lookup, but says nothing about the time window covered, how many decisions are returned, ordering, or truncation — meaningful gaps for a no-parameter query.

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: the first defines the payload, the second gives the action guidance, with the content description front-loaded. Nothing is padded or repeated.

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 zero-parameter lookup with no output schema, the description does the important work of sketching the returned fields. It is nearly complete; only the scope of 'recent' (time window/volume) and the read-only nature are left implicit.

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 there is no parameter semantics to document; the baseline for a zero-param schema is 4. The description correctly adds no misleading argument detail.

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 resource — decisions (approved/rejected, decider, notes) about the caller's earlier requests — which is far more than a restatement of the name. It does not, however, distinguish itself from the sibling acme_check_approval, which plausibly covers overlapping territory.

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 provides a clear trigger condition: 'Check it before retrying something, and follow the notes.' That tells the agent when to call it. No alternative tool is named or excluded, so it stops short of full routing guidance.

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?

No annotations are provided, so the description carries the full burden. 'Add' implies mutation, but it does not disclose permissions, whether the note is appended, whether the customer must exist, or if the operation is reversible. Minimal context beyond the verb.

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 efficient, front-loaded sentence with no wasted words. However, its brevity reflects under-specification rather than optimal conciseness; structurally it is tight.

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 no annotations, no output schema, and only 33% parameter coverage, the description is far too thin. It omits prerequisites, parameter roles, justification context, and return behavior, leaving the agent without essential operational details.

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 only 33% (only justification has a description). The description adds no parameter meaning; email and note remain undocumented, and it does not explain the justification requirement, so it fails to compensate for the coverage gap.

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 (Add) and resource (note to a customer's CRM record). It is distinguishable from siblings like crm_find_customer and crm_update_plan, but it does not explicitly differentiate itself or name alternatives.

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, prerequisites, or alternatives. The agent is not told whether it must first find the customer with crm_find_customer or what conditions require this tool.

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 full behavioral burden. 'Find' implies a read operation, but nothing states whether it is read-only, whether matching is exact or fuzzy, how many results come back, or what approval the 'justification' parameter implies.

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 efficient sentence with the verb and resource front-loaded and zero filler. It is arguably too terse to earn a top score, 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 explained. However, for a search tool the missing pieces are match semantics (exact vs. substring), result limits, and the approval context hinted at by the 'justification' parameter, leaving moderate gaps.

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?

Coverage is 50%: the 'justification' param is documented in the schema, while 'query' has no schema description at all. The description partially compensates by naming the fields the query matches (email, name, company), but says nothing about format, delimiters, or partial-match behavior.

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 (Find) and resource (customers) plus the three lookup fields (email, name, company), which is enough to distinguish it from the CRM mutation siblings crm_add_note and crm_update_plan. It stops short of explicitly contrasting with any sibling, so it lands at 4 rather than 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?

There is no statement of when to use this lookup versus alternatives, no prerequisites, and no indication of what happens when multiple customers match. An agent gets a purpose but no routing guidance.

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?

No annotations are provided, so the description carries the full behavioral burden and largely drops it. 'Cancel it' is clearly destructive/possibly irreversible, yet there is no word on consequences, billing/proration effects, permission requirements, or approval behavior; only the plan-value enumeration adds anything concrete.

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, and the allowed values are packed inline rather than padded into extra sentences. It is efficient, though the extreme brevity leaves gaps that structure alone cannot fix.

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 mutation tool with zero annotations, no output schema and only 33% schema coverage, the description leaves too much unspecified: no side effects, no permission/approval semantics despite the approval-oriented 'justification' parameter, and no indication of what a successful call returns or changes.

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 low (33%) and 'plan' has no enum in the schema, so the description's value list (free, starter, pro, team, cancelled) meaningfully compensates for the most important parameter. It adds nothing about 'email' (self-evident) or how 'justification' interacts with approval beyond what the schema already says.

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 ('Change a customer's plan') and enumerates the allowed target values, which is more than a bare restatement. It doesn't explicitly contrast itself with any sibling, but the CRM-namespace siblings are clearly distinct operations, so disambiguation is not really at risk.

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 (change or cancel a plan) but gives no when-to-use framing, prerequisites, or exclusions. It never mentions that a customer likely needs to exist first (crm_find_customer) or that the approval-gated nature of some calls matters here — usage is inferred rather than stated.

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?

No annotations and no output schema, so the description carries the full behavioral burden and does not meet it. It omits whether sending is irreversible, whether the message is queued or delivered immediately, whether approval is required, and what the result looks like — the schema's own 'justification' field hints at an approval flow the description never explains.

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 short, front-loaded sentence with no filler — structurally clean and immediately readable. It is efficient, though the brevity comes at the cost of the guidance and behavior details a send tool needs.

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 mutation tool with zero annotations, no output schema, and 25% parameter coverage, the description is far too thin. It never addresses irreversibility, approval requirements, or return behavior, leaving real gaps for an agent deciding whether and how to invoke it.

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 25%: only 'justification' is documented, and the description adds nothing about any parameter. It doesn't clarify whether 'to' accepts multiple recipients, whether 'body' is plain text or HTML, or how the approval-related 'justification' interacts with sending.

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+resource ('Send an email') and pins down the sender identity (support@acme.com), which is genuinely useful scoping information an agent cannot infer. It doesn't need to distinguish itself from siblings since no other sibling sends email, but it says nothing about scope (single vs. bulk, who may be addressed).

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 approval/decision siblings (acme_check_approval, acme_ask_user, acme_recent_decisions) that appear adjacent to this tool. An agent gets no signal about whether an approval step must precede a send.

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?

No annotations exist, so the description must carry the behavioral burden. It discloses the ordering and that only a short preview is returned, which usefully signals 'browse then read in full'. However, it says nothing about read-only safety, pagination or result limits on a potentially large inbox, and the schema's justification field hints at an approval workflow the description never explains.

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 zero filler that front-loads the resource and scope before the ordering and preview detail.

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-value explanation is unnecessary, and the description covers scope and ordering. The only real gap is the absence of any statement about result volume, limits or pagination for a shared inbox that could be large.

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% for the single justification parameter, so the baseline is 3. The description adds nothing about that parameter, though none is needed given the schema text is self-explanatory.

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 (support emails in the shared inbox), plus ordering (newest first) and a preview hint. It is clearly distinguishable from inbox_read, which implies fetching one full email, though it never names a sibling 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?

Usage is implied by the verb 'List' versus siblings like inbox_read, but there is no explicit when-to-use guidance, no mention of when inbox_read should be preferred, and no mention that some calls require approval.

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 full burden. It usefully discloses the mutation ('mark it as read'), but says nothing about whether that write is reversible, what permissions/approval are needed, or what the read returns.

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 action and resource, and it uses the remaining words to disclose the state change. 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?

A mutating tool with no annotations, no output schema, and an approval-flavored justification parameter sitting alongside approval siblings (acme_check_approval, acme_ask_user). The description should at least indicate the approval/permission model and whether the read state change can be undone.

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 only 50% (message_id has no description) and the description adds no parameter meaning at all. It does not clarify the message_id format or the approval semantics of the justification field that the schema only vaguely hints at.

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?

Names a specific verb (read) and resource (one support email) plus the side effect of marking it read, which cleanly separates it from the sibling inbox_list. It does not explicitly name the alternative, but the scope distinction is unmistakable.

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: you read one message after presumably finding it via inbox_list. There is no statement of when to use this versus inbox_list or any other sibling, 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?

No annotations are provided, so the description carries the full burden. It does disclose one genuine behavioral detail beyond the name — that returned charges include any refunds already applied — which is useful. However it says nothing about permissions, pagination, or approval requirements, which the 'justification' parameter in the schema implies are relevant.

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 efficient sentence with the resource and scope front-loaded and zero filler. It is appropriately sized for a simple list operation, though it is arguably too terse to earn 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?

An output schema exists, so return values need not be explained, but with zero annotations, an undocumented required parameter, and no mention of approval or auth context despite an approval-oriented 'justification' field, the definition leaves material gaps for a payments-related tool.

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 only 50%: customer_email is undocumented in the schema, and the description never clarifies its format or how it is matched. The description adds no meaning to either parameter, so it fails to compensate for the coverage gap.

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 (List) and specific resource (a customer's card charges), and adds a scope qualifier ('with any refunds already made'). It does not explicitly differentiate itself from siblings like payments_refund or payments_transfer, but the read-oriented framing makes its role reasonably inferable.

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 guidance on when to use this tool versus alternatives such as payments_refund or crm_find_customer, nor any prerequisites (e.g., customer must exist, approval may be required). The agent is left to infer usage entirely from the 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?

With no annotations, the description carries the full behavioral burden and largely drops it. For an irreversible financial mutation it says nothing about required permissions, whether refunds need approval, idempotency, time limits on how far back a charge can be refunded, or what happens on failure. The only behavioral hint is 'all or part', which implies partial refunds are supported.

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 and the key scope qualifier ('all or part') in place. It is efficiently written, though the terseness leaves no room for the operational detail this tool needs.

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 4-parameter, 3-required financial mutation with no annotations, no output schema, and 25% schema coverage, the description is well short of complete. It omits approval flow, permission requirements, refund limits, and error behavior, all of which an agent needs before invoking it.

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 only 25% (just 'justification' is documented), so the description must compensate, and it mostly does not. It implies 'amount' may be a partial value, but 'charge_id' and 'reason' get no added meaning such as accepted formats or valid reason values, and there are no enums to fall back on.

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 specific verb ('Refund') and resource ('card charge') plus the scope 'all or part', which is enough to distinguish it from siblings like payments_transfer or payments_list_charges. It stops short of explicitly naming a sibling or contrasting itself with one, so it lands at 4 rather than 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?

There is no statement of when to use this tool versus alternatives, no preconditions, and no mention of the approval workflow that the sibling tools (acme_check_approval, acme_ask_user) and the 'justification' parameter clearly imply. The agent is left to infer everything about context.

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 full burden, yet it discloses nothing about irreversibility, required permissions, approval workflow, or rate limits — all critical for a money-movement operation. Only the word 'wire' hints that this is a real, irreversible bank action; the optional justification param suggests an approval flow that the description never mentions.

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 no waste and the key action front-loaded. It is arguably too terse for the risk level, but judged purely on structure it is efficient and readable.

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 high-stakes financial mutation with no output schema, no annotations, and near-zero parameter documentation, the description is materially incomplete. An agent could invoke it without knowing about approval gates, irreversibility, or the meaning of the required fields.

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 only 25%, and the description compensates for none of it: to_account, amount, and memo are unexplained (currency? format? internal vs external account?). The only documented param, justification, is described in the schema, not the description.

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 (send) and resource (bank transfer/wire) plus the source account (Acme's), which is enough to distinguish it from payments_refund and payments_list_charges. It never names a sibling explicitly, but the action and scope are 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 prerequisites, and no alternatives are named. An agent cannot tell from the text when a transfer is preferred over a refund or when approval (via acme_check_approval) must be sought first.

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