Subsidy-Exposure & Quota-Cliff Watch

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 it discloses almost nothing: no statement of read-only vs mutating behavior, no return shape, no pagination or refresh semantics. 'Current' hints at freshness but there is no substantive behavioral context for an unannotated tool.

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?

It is a single short, front-loaded sentence with no filler, so it is structurally compact. However, the brevity comes at the cost of substance, making it under-specified rather than genuinely concise.

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 annotations, no output schema, an undocumented parameter, and ambiguous sibling relationships, the description would need to do much more work. It orients the agent to a pool and 'events' but omits everything else needed to invoke the tool confidently.

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, so the description must compensate and does not. 'Your pool' loosely implies pool_id, but gives no format, source, or expected value, leaving the only parameter semantically undefined.

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 is a noun phrase ('Current typed diff events for your pool') rather than a verb+resource statement, and the name 'check_pool' does not line up with what is described (fetching diff events). An agent can guess it reads event data for a pool, but it cannot tell what 'typed diff events' means or how this differs from siblings like precommit_query or shadow_price.

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 preconditions, and no mention of the sibling tools (precommit_query, register_pool, shadow_price) that could be alternatives. The only implicit signal is 'your pool', which is too weak to route the agent.

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 behavioral burden, and it does disclose meaningful non-obvious traits: per-call cost ($0.01/call), a free first query per operator, and the x402 payment flow via the X-PAYMENT header upon a 402 response. It omits failure modes, retry behavior, and whether verdicts are cached, so it is not fully transparent.

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, front-loading the verdict semantics before the pricing/payment detail, with no filler. Slightly dense due to nested jargon (x402, 402 challenge) but 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?

The payment behavior is well covered, but for a single-parameter mutation-adjacent query tool with no output schema and no annotations, the description leaves the input parameter undocumented and gives no sense of the verdict's meaning or freshness. Adequate but with a clear 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?

There is one parameter (pool_id) with no schema description and the description never mentions it, so 0% coverage is not compensated. An agent must infer from the name alone what identifier is expected or what format it takes.

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 outcome (a pre-commit verdict) with the enumerated possible values OPEN / AT_RISK / CLIFFED, which tells an agent what it gets back. It names the operation ('query') and its subject, but does not differentiate itself from sibling tools like shadow_price or check_pool.

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, when-not-to-use, or alternative-selection guidance is given; the siblings (check_pool, shadow_price) are never referenced. The only 'when' information is a payment mechanic (a 402 challenge), which is not about tool selection.

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 disclosure burden. It implies a write operation via 'register' but does not describe permissions, idempotency, error behavior, or what happens if the pool already exists.

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 a single front-loaded sentence with no filler. It is appropriately sized for the amount of information it conveys, though the information itself is thin.

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 a nested object parameter, no annotations, and no output schema, the description is too sparse. It does not explain the budgeted terms structure, expected registration behavior, or error cases.

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. It vaguely identifies budgeted_terms as 'structured terms' but does not explain their structure or meaning, and pool_id is left entirely unexplained.

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: register a pool with a budgeted quota definition. It is clear what the tool does, but it does not distinguish itself from related siblings like check_pool or precommit_query.

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 indication of when to use this tool versus alternatives, nor any prerequisites or conditions. The description only states what the tool does, not when it should be selected.

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, yet it discloses nothing about whether this is a read or mutation operation, permissions, side effects, or response shape. The phrase "shadow price" is conceptual and does not clarify runtime behavior.

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 a single short sentence with no wasted words, but it is drastically under-specified rather than concise. Brevity here comes at the cost of nearly all useful 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?

For a tool with two required nested objects, an optional parameter, no output schema, and no annotations, the description is completely inadequate. It does not explain inputs, outputs, or behavior sufficiently for correct invocation.

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 three parameters, including two required nested objects (usage and metered) and an optional number. The description adds no meaning about what these objects should contain or how subsidized_paid_usd affects the computation.

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 restates the tool name ("shadow price") and adds a vague qualifier about metered vs. subsidized usage, but it never states a concrete action such as calculating, estimating, or returning a price. It does not distinguish this tool from siblings like check_pool or precommit_query.

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, when not to use it, or which sibling alternatives apply. The agent is left to infer usage entirely from the name and the skeletal schema.

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