InfraPulse

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

Annotations already declare idempotentHint and the read/write safety profile, but the description adds genuinely new behavior: it discloses the real side effect (reserving private account credits) and the explicit boundary that provider work is not performed. It does not say whether or how a reservation is released or expires.

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 zero filler; the core action comes first and the scoping caveat follows. 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?

An output schema and annotations exist, so return values and safety are covered, but for a tool with 8 properties, nested `payload`, and a three-way anyOf this is underspecified. An agent cannot tell which input mode to pick (quoted operation vs. raw credits vs. payload wrapper) from the description.

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 13% (only request_id is documented), so the description carries the burden — yet it explains none of the 8 parameters. The anyOf alternation between quote_id, credits, and payload, and the distinction between request_id and idempotency_key / provider_intent, are left entirely opaque.

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 ("Create an idempotent prepaid authorization") with scope ("for a quoted operation"). The clause "does not execute provider work" implicitly separates it from the sibling `execute`, 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?

Implies the tool is a pre-execution step and that payment is reserved rather than charged, which helps an agent position it relative to `execute`. However, it never states the prerequisite (obtain a quote via `quote` first) or when-not-to-use, leaving the ordering to inference.

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 it non-read-only, idempotent, non-destructive, and the description adds real auth context (owner approval, scopes stored by InfraPulse, bearer reuse). It omits, however, that the tool also drives follow-up state changes (suspend, resume, refresh_funding), so an agent reading only the description would believe this is purely an onboarding call. Not a contradiction with annotations, but an incomplete behavioral picture.

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 dense sentences with no filler, and the two credential paths are front-loaded. Efficient, though the space is spent on onboarding at the expense of the tool's other modes.

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 6-parameter, multi-action tool with an anyOf schema and follow-up actions including suspend and refresh_funding, the description covers only the account-linking path. An agent would not learn from the description that this tool manages connection lifecycle state, which is the main completeness 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%, so the schema already explains scopes, request_id, connection_id, and agent_id — the description mostly restates the scopes behavior. It adds nothing about the action enum or the anyOf branch structure that governs which parameters are required.

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 ('Connect an InfraPulse identity to the MCP workflow') and enumerates two credential paths (OAuth with owner approval vs. machine self-registration). However, it never distinguishes this tool from the sibling 'authorize', which an agent could reasonably confuse with connecting an identity.

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 clear internal routing (existing customer accounts -> OAuth; autonomous machines -> /v1/agents/register), which is genuinely useful. But it offers no guidance on when to use this tool versus 'authorize' or 'discover', and says nothing about when to call it with action=status/approve/suspend/resume rather than creating a new connection.

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 establish readOnlyHint, idempotentHint, destructiveHint=false, and closed-world scope, so the bar is lower; the description nonetheless adds real behavioral context by explicitly enumerating the side effects it will not cause (no provider authorization, no credit spend, no account changes, no release publishing). It stops short of describing response shape or pagination, but with an output schema present that is acceptable.

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 tightly packed sentences, front-loaded with the affirmative purpose before the boundary clauses. Zero filler, though the second sentence is a dense four-item negative list that takes a moment 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?

With rich annotations, a fully documented single-parameter schema, and an output schema present, the description covers everything an agent needs to decide to call this and how. Minor gap: it does not clarify that omitting 'view' is the default capabilities mode, which is left entirely to the schema.

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 'view' parameter is fully enum-documented with an explanation of what omitting it does. The description restates the view names (readiness, safe_checks, test_catalog, evidence) but adds no formatting or selection guidance beyond what the schema already provides, 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 and resource ('Discover InfraPulse production capabilities and optional read-only audit views') and implicitly differentiates itself from siblings by declaring what it does not do (authorize, spend credits, change accounts, publish releases), which maps onto authorize/execute/quote. It never names a sibling explicitly, so the differentiation is inferential rather than stated.

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 negative framing ('does not authorize... spend credits... change accounts... publish releases') steers the agent away from using this for mutations, and the schema notes that omitting 'view' gives plain capabilities discovery. However, the description itself gives no explicit when-to-use or when-to-choose-an-alternative guidance relative to authorize, connect, quote, or execute.

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 destructiveHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds value beyond that by disclosing real-world cost (may consume prepaid credits) and the fact that it mutates an external provider system — exactly the kind of consequence-an-agent-should-know context that annotations alone don't 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?

Two compact clauses with the scope and prerequisites front-loaded and no filler. It could be tightened slightly, but every sentence 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?

Output schema exists and annotations are rich, so return values and safety are covered. However, for a 9-parameter, open-world, destructive mutation tool with 22% schema coverage, the description omits too much about parameter intent and the task/input contract to be considered complete.

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 22% across 9 parameters, so the description must compensate and does not: it names request_id and authorization_id but adds nothing beyond their schema descriptions, and leaves task, input, provider_id, provider_intent, agent_id, metadata, and timeout_seconds entirely unexplained in either place. The agent cannot tell from the definition how task/input differ or how provider selection works.

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 (execute) and a resource (authorized provider work) and ties the tool to the authorize-then-execute workflow by requiring an authorization_id. The resource is still abstract — 'provider work' doesn't tell the agent what domains or task types are valid, which is a gap given the generic sibling name 'execute'.

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 states a hard prerequisite (a canonical authorization_id from the authorize step), which implies this runs only after authorization. There is no explicit guidance on when not to use it, how it relates to siblings like quote or verify_receipt, or what to do if authorization is missing.

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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds real value by clarifying that no credits are reserved and no provider work runs — the main thing an agent might fear about a pricing call. However, it says nothing about quote validity window, determinism inputs, or how the quoted price relates to the eventual authorization amount.

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 short sentences, zero filler, with the primary purpose front-loaded and the negative side-effect clause immediately after. 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?

This is a high-complexity tool with nested objects, a dual input shape, and 19 undocumented parameters, and the description does not address any of it. The output schema means return values need not be explained, but the input surface and quoting behavior are left almost entirely unexplained for a tool this complex.

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 19 parameters and 0% schema description coverage, the description carries the full burden and provides nothing — not even what "task" or "sector" mean, nor the role of budget_limit_credits, policy_profile, providers_allowed, or execution_constraints in shaping the price. It also fails to explain the two accepted invocation shapes (flat task vs. nested payload) allowed by the anyOf.

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 ("Get a deterministic price quote") and situates it in the pipeline relative to authorization and execution, which maps onto the authorize and execute siblings. It stops short of naming those tools directly, so the differentiation is implied 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?

Gives clear timing guidance: call this before authorization or execution. That is a genuine ordering constraint an agent needs. It does not say what to do if the quote is rejected, stale, or when a quote is unnecessary, so there are no explicit exclusions.

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?

The annotations already provide readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is well covered. The description adds only modest behavioral context beyond annotations, such as the signed nature of the receipt and the explicit no-state-change guarantee, but does not disclose additional traits like exact response semantics (covered by output schema) or failure modes.

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, focused sentence that front-loads the primary action and key mode of identification, then appends the behavioral guarantee. There is no filler, repetition, or unnecessary detail, making it highly scannable for an agent.

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 the presence of a rich output schema and safety annotations, the description covers the core usage scenario well. The main gap is the undocumented 'payload' parameter, which leaves the agent uncertain whether payload is a valid alternative identity and whether it behaves differently from receipt_id or receipt. Overall, it is nearly complete but not fully self-sufficient.

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 burden of explaining parameters. It explicitly names receipt_id and receipt object, which covers two of the three accepted inputs, but it omits 'payload' entirely and gives no detail on the inner structure of the object parameters. Thus it partially compensates for the schema gap but is incomplete.

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 clearly states a specific verb ('Verify'), a specific resource ('an InfraPulse signed receipt'), and the two accepted ways to identify it ('by receipt_id or receipt object'). It also adds a key differentiator, 'without changing account or provider state', which aligns with the read-only nature and distinguishes it from the sibling tools like execute and quote.

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 gives clear context for when to use the tool: when verifying a signed receipt by ID or object, without side effects. It does not explicitly name alternatives or exclusion conditions, but the sibling tools (authorize, connect, discover, execute, quote) are sufficiently different that the usage context is unambiguous.

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