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

With annotations declaring readOnlyHint=false and destructiveHint=false, the description usefully explains why a read-looking assessment is a mutation: it 'creates a metered asynchronous job and may retain delivery state.' Disclosing that the call is metered (cost-bearing) and async is exactly the kind of context annotations cannot convey, and the negative list ('No fetching, inference, FAHCE, approval or payment') bounds side effects.

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 key fact (job, not report) is front-loaded and the sentences are information-dense, but the description repeats itself: 'without revising seller terms' and 'Does not revise seller terms' say the same thing twice. Terms like 'FAHCE' are used without explanation, adding noise rather than signal.

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 an async, metered job tool with an output schema, the description covers the essential contract: it returns a handle, the report arrives via get_result, and some outcomes may come back as a resumable manifest. Combined with the idempotency and retry notes in the schema, an agent has enough to call it correctly, though the undefined jargon leaves a small gap.

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?

Both parameters are fully documented in the schema (100% coverage), including the retry/request_id reuse contract, and the description only alludes to session_id via 'your retained session.' Nothing in the description adds syntax or constraints beyond the schema, 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?

States a specific operation: a deterministic readiness assessment over the caller's retained session, and explicitly separates itself from get_result by saying it 'Returns a job, not the report' which must be polled. The scope exclusions ('Not seller certification or commercial clearance') sharpen the boundary. It stops short of distinguishing itself from export_offer, so an agent choosing between those two still has to infer.

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 downstream step ('poll get_result for signed readiness JSON'), which is real usage guidance, and it names what the result is not. However, there is no explicit statement of when to call this versus export_offer or get_status, and no stated prerequisite such as 'call start_session first' beyond the implicit 'your retained session'.

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?

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false), the description discloses that the call creates a metered asynchronous job, that delivery state may be retained, and that the result is neither publication nor certification. Metering and async-job behavior are exactly the cost/side-effect facts an agent cannot get from the hints, and they are consistent with idempotentHint=false.

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 verb and exportable artifacts are front-loaded, and each subsequent sentence adds a distinct fact (parts retrieval, non-publication, metered async job, state retention). Some phrasing is dense and legalistic ('explicitly incomplete response without inference'), but there is little waste.

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, the description usefully explains that oversized results are split into a resumable manifest fetched via get_export_part, which tells the agent what to expect back. It does not state what a small/complete export returns (inline payload vs. job handle/status), leaving a minor gap about the immediate response shape.

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 schema itself already explains the format enum, the request_id retry/reuse rule, and the session_id identity requirement. The description adds only indirect meaning (large responses produce a manifest split into parts), so the schema does the heavy lifting and a 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?

The description gives a specific verb ('Export') and enumerates the exportable artifacts: saved offer, proposed plan, or explicitly incomplete response. It also names the sibling get_export_part for the split-retrieval path, so the agent can distinguish it from a part-fetch. The purpose is clear, though the phrase 'without inference' is jargon that slightly muddies the statement.

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 explicitly routes large responses to the resumable manifest and directs the agent to get_export_part, which is real alternative-selection guidance. It also draws a boundary constraint ('does not revise seller terms'), but it gives no guidance on when to prefer export_offer over get_result, get_status, or assess_offer_readiness.

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=false, idempotentHint=false and destructiveHint=false; the description adds real context beyond them by noting the call creates a metered asynchronous job and may retain delivery state, which explains why a 'retrieve' is not read-only. However, 'without inference' and 'Does not revise seller terms' are cryptic and do not clarify retry, cost, or state-retention semantics.

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 purpose is front-loaded and the sentences are short, but the second half drifts into clauses that do not help an agent decide or invoke: 'Does not revise seller terms' is unrelated to retrieving a part, and 'without inference' is unexplained jargon.

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?

All four required parameters are documented in the schema and there is no output schema, so the description only needs to cover flow and side effects. It covers metering and state retention but leaves open what a part response contains, whether parts can be fetched in parallel, and what happens if a part is missing or has a hash mismatch.

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%, including meanings for index, export_id, request_id and session_id, so the schema already carries parameter semantics. The description adds only the general verification requirement, not per-parameter meaning, 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 first clause gives a specific verb and resource with scope: 'Retrieve one existing resumable export part from your session.' An agent can tell this fetches a single part rather than the whole export (get_result) or status (get_status), though no sibling is named 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?

It implies the usage pattern: retrieve every part and verify hashes before claiming completion, so the agent infers iteration until all parts are received. There is no explicit when-not or pointer to an alternative sibling such as get_result, so guidance is implied 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?

Annotations declare readOnlyHint=false and openWorldHint=true, and the description explains the reason in operational terms: polling is metered and may wake queued processing, and it is explicitly not a side-effect-free read. That is exactly the non-obvious cost/effect information an agent needs before calling a repeated polling endpoint, and it is consistent with 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?

Short, front-loaded sentences that each carry operational content: ownership, non-completion statuses, no-duplication, metering, and side effects. The fragment "No inference." is cryptic enough to cost a point since its meaning (do not assume completion?) has to be guessed.

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 polling tool with no output schema, the description supplies the key state vocabulary (pending/processing/uncertain) and the cost model. It does not indicate what a completed response contains or how statuses map to finality, which leaves a modest gap for an agent deciding when to stop polling.

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 one parameter at 100% schema description coverage, the schema already documents job_id as a stable UUID to poll rather than redispatch. The description reinforces 'poll this same job' but adds no new format, constraint, or edge-case meaning beyond that. 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 ("Read a job") plus the ownership scope ("owned by your authenticated client"), which is more than a restatement of the name. It does not explicitly distinguish itself from the nearby sibling get_status, so an agent must infer whether job polling and general status polling are the same thing.

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 real when-to-use context: pending/processing/uncertain are explicitly not completion, so the agent should poll the same job rather than dispatch replacement work. It also warns against duplicating an uncertain message. It omits any cadence guidance and never names an alternative sibling tool, 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?

Annotations already declare it is not read-only, not idempotent, and not destructive; the description adds real context beyond that by disclosing the metered asynchronous job, possible retention of delivery state, and the fact that it does not revise seller terms. This is consistent with readOnlyHint=false, since the write effect is job creation rather than data mutation. It does not mention auth or rate-limit specifics beyond 'metered'.

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 the core purpose front-loaded, followed by the return/hand-off behavior and constraints. 'without inference' is slightly cryptic but the rest is waste-free.

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, the description correctly explains that the return value is a job requiring polling, which is the key thing an agent needs. It does not say what the offer status payload contains, but that is a minor gap for a two-parameter 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 100%, with both session_id and request_id fully documented including retry/idempotency semantics, so the description adds nothing parameter-specific. Baseline 3 applies when the schema carries the full burden.

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 the existing agent for the current offer status. It also distinguishes its return shape from the sibling get_result by saying it returns a job to be polled there. It does not differentiate itself from assess_offer_readiness or get_export_part, 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?

The sentence 'Returns a job; poll get_result' gives explicit routing: call this to kick off, then use the sibling to retrieve results. There is no explicit when-not guidance relative to assess_offer_readiness, but the async-job framing makes the usage context 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 destructive=true, openWorld=true and idempotent=false, and the description adds genuinely non-redundant behavior on top: it may 'overwrite seller fields or rebuild retained drafts', invalid values 'reject the entire update', card selections are handled separately, quota is consumed, and dedup is 'bounded by retained session/job lifetime, not an unqualified retry guarantee'. That last caveat usefully qualifies the non-idempotent hint. It falls short of 5 only because the phrasing is compressed to the point of ambiguity in places.

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?

There is little filler, but the text is a single undifferentiated stream of clauses with no front-loading — the core action competes with quota, dedup and refusal notes for the opening position. Undefined acronyms (FAHCE) and bare schema tokens (TOOL_OFFER_INTAKE_V1) force parsing effort that a short structured layout would avoid.

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 mutation tool with no output schema, the description covers the important contract: it returns a stable job, it may return a signed completed result under Prefer: wait, otherwise you poll get_result, and there is no payment or execution side effect. The only notable gap is nothing about failure responses or how the job handle should be retained across sessions.

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 baseline is 3, but the description earns above baseline by enumerating the intake keys (tool_url, docs, customer, pricing, payment, access, invocation, optional job and seller_name) and by stating that all non-enumerated values are strings and that a serialized TOOL_OFFER_INTAKE_V1 schema governs validation. That tells the agent message structure in a way the schema's single string field cannot.

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 and the accepted payload shapes concretely: 'field: value lines, or a JSON-serialized StructuredIntake object', plus product questions, revisions and drafting commands. It also distinguishes itself from the polling sibling by pointing at get_result. It loses a point because the opening is a dense enumeration of value with undefined tokens (TOOL_OFFER_INTAKE_V1, FAHCE) that slow an agent down before it knows the core action.

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 real operational guidance: use 'HTTP Prefer: wait=1 through wait=5' to wait inline, 'Otherwise poll get_result', and 'Never resend uncertain work with a new request_id'. What is missing is any steering against the other siblings (assess_offer_readiness, export_offer) — an agent is told how to wait, not when this tool is the wrong entry point.

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?

Beyond the annotations, the description discloses the idempotency-key retry contract and that no model inference occurs, which is genuine behavioral context an agent needs. Worth noting a tension: 'replaying it returns the same session' reads as replay-safe while the annotations set idempotentHint=false, though the annotation likely refers to the create-new-resource default rather than request_id-keyed replay.

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 short sentences, front-loaded with the core action, then the required-parameter constraint, then the capability boundary. Nothing is padded or redundant.

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 creation tool with no output schema, the description never says what the caller gets back — a session ID, an offer handle, expiry metadata, or a status object. Since no output schema exists to carry that, the return shape is an unresolved gap.

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 request_id property already documents the caller-generated UUID, retry retention, and non-reuse rules. The description's mention of a 'unique request_id' and replay behavior only restates that, adding no new syntax or format detail 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 opens with a specific verb+resource ('Create ... offer conversation') and adds a scoping qualifier ('isolated seven-day'), which lets an agent distinguish it from siblings like send_message or get_status. 'Offer conversation' is somewhat domain jargon, keeping it 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 supplies a retry rule ('replaying it returns the same session') and a negative capability note ('No model inference'), but never states when to call this versus its siblings or what prerequisite state must exist. Usage is implied rather than prescribed.

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