Demurrage for Agent Resource Holds: price the hold, not just the use

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 notes the auth requirement (api_token) and what fields the account state contains, but does not disclose whether this is a read-only operation, what happens on an invalid token, or any rate/permission constraints.

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 single line is front-loaded and free of filler, which is good. However, the fragment style reads as under-specification rather than purposeful brevity for a tool an agent must act on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with no annotations and no output schema, the description is thin: it never states the operation type (read-only) or behavior on failure, leaving the agent to infer how to call it reliably.

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%, with only api_token present. The description confirms the token is required but adds no meaning beyond the schema: no expected format, source, or scope of the token. It restates rather than compensates 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 names a specific resource (the caller's own account state) and enumerates what it returns: trial remaining, fleet plan, service charges. That distinguishes it from the hold/capsule siblings, though the verb is only implied and the fragment style is terse.

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 is given and no alternatives are named. The sibling tools (demurrage_query_hold, demurrage_register_hold, etc.) operate on holds, but the description never says when an agent should reach for account state instead of them.

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, and the step list ('budget debit', 'cap snapshot-and-release') does hint that this mutates budget state and takes a cap snapshot, which is useful signal. But it never states permissions needed, idempotency, reversibility, or whether the debit is committed or merely previewed, leaving the safety profile ambiguous for a multi-step operation.

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 in a single dense sentence and the follow-up is brief. The 'Requires api_token, hold_id' sentence is largely redundant with the schema's required array, which costs a little.

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?

This is a compound operation (accrual, notice ladder, budget debit, cap snapshot-and-release) with no output schema, no annotations, and undocumented parameters, yet the description never explains what any step means or what the evaluation returns. An agent can identify the tool but not predict its effect or result.

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 neither parameter is explained in the description — 'Requires api_token, hold_id' only restates the required list already present in the schema. No format, provenance, or scoping semantics for hold_id are added, so the description does not 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 ('Evaluate') and resource ('a hold') and enumerates the sub-operations it performs: accrual, notice ladder, budget debit, cap snapshot-and-release. However, it never distinguishes itself from siblings like demurrage_query_hold, demurrage_release_hold, or demurrage_account, so an agent cannot fully route between them from the text 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 and no mention of alternatives, despite four plausible sibling tools (query, register, release, account). The agent must infer that 'evaluate' is the composite operation, which is not 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?

With no annotations, the description carries the full burden, and it does disclose genuinely useful behavior: a one-time free query per operator, a per-query charge via x402, and fleet-plan inclusion. However it never states that the operation is read-only/non-mutating, what happens on payment failure, or how the x402 flow behaves, so key behavioral traits remain unstated.

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 front-loads the returned values, then the pricing caveat, then the parameter summary. Nothing is padded, though the telegraphic style makes some clauses (x402, fleet plan) hard to parse.

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?

The description partially compensates for the missing output schema by enumerating the returned tariff fields, and it covers payment behavior. But with 0% parameter coverage and no annotations, gaps remain around x_payment format and error/read-only 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?

Schema description coverage is 0% for all three parameters. The description only restates the schema's required/optional split ('Requires api_token, hold_id; optional x_payment') and adds no format, meaning, or expected value for any of them (e.g., what x_payment should contain).

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 operation (tariff query on a hold) and enumerates exactly what it returns: free time left, tier, next-hour cost, accrued, idle ratio. That is enough to tell it apart from a generic evaluate or register tool, though it never explicitly contrasts itself with siblings like demurrage_evaluate_hold.

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 call this versus demurrage_evaluate_hold or demurrage_account. The only context offered is the pricing model (one free query per operator, then $0.005/query), which describes cost rather than usage conditions or prerequisites.

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 does disclose meaningful behavioral traits: a one-free-registration-per-operator quota, $0.01/hold x402 pricing, and fleet plan inclusion, which is real value beyond the schema. However, it says nothing about what the hold actually does to the resource (exclusivity, duration, reversibility) or side effects of registration.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and compressed into a single sentence plus a pricing parenthetical; no filler. The dense pricing clause is information-rich but slightly crowds out more essential invocation 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?

For a mutation tool with no annotations, no output schema, 7 parameters at 0% schema coverage, and a nested 'state' object, the description is far too thin. It omits the effect of holding, payment flow for x_payment, the structure of state, and any error/permission behavior.

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 7 parameters, so the description must compensate, but it only re-lists parameter names ('Requires api_token, agent, resource_class, task, budget; optional state, x_payment') without explaining meaning, format, or units (e.g., what budget is denominated in, what x_payment carries). Naming params already visible in the schema adds little.

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+resource: 'Register a hold on a pooled resource.' This is clearly distinguishable from sibling actions (release, query, evaluate, account), though the description never explicitly names a sibling to contrast with.

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 or when-not-to-use guidance is given, and no alternative sibling (e.g., demurrage_evaluate_hold or demurrage_query_hold) is named as the path for other cases. The pricing/quota note hints at cost considerations but is not usage 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?

With no annotations, the description carries the full behavioral burden, yet it only says the hold is released 'voluntarily' and lists two required inputs. It does not disclose whether the mutation is reversible, what permissions or token scope are needed, what side effects occur, or what the response looks like.

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 appropriately short and front-loads the action. The second sentence is somewhat redundant with the schema's required fields, but the overall definition is not bloated.

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 no annotations, no output schema, and zero parameter description coverage, the description is too sparse. It omits the behavioral and domain context an agent would need to invoke this safely, especially how voluntary release differs from sibling operations.

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, but it merely repeats the required parameter names. It adds no meaning about where api_token comes from, what format hold_id uses, or what each parameter controls. The parameter names are self-explanatory but the description adds almost nothing beyond the schema's required list.

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 and resource ('release a hold') and adds a useful qualifier ('voluntarily'), so the core action is clear. However, it does not differentiate this tool from siblings like demurrage_restore_capsule or demurrage_register_hold, leaving an agent to infer the distinction from the 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?

It provides no explicit when-to-use guidance, no conditions for choosing this tool over alternatives such as restore_capsule or query_hold, and no prerequisites beyond listing required inputs. The agent receives no routing help.

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, and it does disclose two real behavioral traits: the capsule hash is verified and tampered capsules are refused. It says nothing about permissions, whether the operation is idempotent or reversible, or what happens to an existing hold, so significant disclosure gaps remain.

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 action front-loaded and the requirement list relegated to the back. The parenthetical is compact and informative rather than wasted, though the trailing required-parameter list is redundant with the schema.

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, unattended operation with no annotations, no output schema, and no explanation of the opaque 'budget' parameter or the failure mode on a hash mismatch. The hash-verification note helps, but an agent still lacks what it needs to invoke this safely and 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% for three parameters, so the description is the only source of meaning. It merely restates the required parameter names ('Requires api_token, capsule_id, budget') without explaining budget units or limits, token format, or capsule_id provenance, adding essentially nothing over the schema's required list.

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 (restore a snapshot capsule) plus the target scope (a NEW hold), which is more specific than the sibling hold-management tools. It does not explicitly contrast itself with demurrage_register_hold or demurrage_release_hold, so the differentiation is only partial.

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 this tool should be chosen over the sibling hold tools, nor any prerequisites or exclusions beyond the parenthetical about tampered capsules. The phrase 'into a NEW hold' hints at the use case but the agent must infer the selection criteria itself.

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