PHION Evidence

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds that the index is 'free' and 'generated from canonical inventory', which is useful freshness/provenance context, but it says nothing about pagination, size, or format of the full index.

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 nature of the resource before the usage clause. No wasted words.

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-param read tool with full annotation coverage, the safety and usage essentials are present, but the 'complete index' likely returns a large payload and the description doesn't hint at size or output shape (no output schema exists to compensate). Could say more about what the index contains.

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 the baseline is 4. The description correctly implies no filtering input is required, consistent with a full-index operation.

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: provides a 'complete PHION service index'. It says what the tool returns and frames it as an inventory inspection. It doesn't explicitly distinguish itself from sibling phion_search_services, which likely offers a filtered view.

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?

'Use when the agent knows a capability or wants to inspect the full network' gives a usage condition, but it doesn't contrast against siblings like phion_search_services or phion_get_service. The guidance is implied rather than explicit 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?

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is partly covered. The description nonetheless adds real substance: budget enforcement, persistent idempotency, acceptance-criteria evaluation, a signed completion envelope, and the pricing note ('no gateway surcharge'). It stops short of describing failure/retry behavior or the dry-run 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?

Two tight sentences, front-loaded with the gateway purpose and flow, with a pricing clause that earns its place. Dense but not padded; density does cost some readability for a 7-parameter tool.

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 7-parameter, nested-object, no-output-schema mutation tool, the description leaves meaningful gaps: dry-run behavior, input shape, atomic budget units, acceptance-criteria pointer syntax, and what happens when criteria fail are all unaddressed. Both schema and description are thin on parameters.

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, and it only partially compensates. It conceptually covers budget (max_budget_atomic), idempotency (idempotency_key), acceptance criteria, and target_service, but says nothing about the 'atomic' unit format, the JSON-pointer syntax for acceptance criteria, the objective field, or what dry_run does.

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 and resource ('execute one selected PHION service') and frames the tool as a 'Universal PHION execution gateway' that also budgets, idempotency-checks, evaluates acceptance criteria, and returns a signed envelope. That is far more informative than restating the name, but it never explicitly contrasts itself with siblings like phion_preflight or verify, so an agent must infer the boundary.

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?

'Execute one selected PHION service' implies this is the terminal step after discovery/selection, but no condition is given for choosing this over phion_preflight or verify, and no prerequisites or exclusions are stated. Usage is deducible from context rather than spelled out.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds that the returned contract is 'canonical' and matched exactly, but says nothing about not-found behavior or what the contract contains.

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 the verb, scope, and accepted keys; no filler or redundant restatement of the name.

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 read tool with rich annotations and no output schema, the description covers the essentials. It could add a word on miss/error behavior, but nothing an agent needs to invoke it correctly is missing.

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% and the only property is an undescribed 'serviceId' string, so the description carries the burden. It adds real meaning by stating the key accepts either a service id or an MCP tool name, though it omits id format or case-sensitivity details.

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?

Specific verb ('Retrieve') plus resource ('PHION service contract') with a scope qualifier ('one exact canonical') that implicitly contrasts with the plural search sibling. It does not name an alternative tool explicitly, so it falls just short of the top band.

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 states that lookup is by service id or MCP tool name, but gives no guidance on when to use this versus phion_search_services, phion_resolve, or phion_discover. No prerequisities or exclusions are mentioned.

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, idempotentHint, destructiveHint=false and openWorldHint=false, covering the safety profile. The description adds 'free' and 'does not charge', which is a useful cost behavior not in annotations, but it does not describe return format, permissions, or what a preflight actually validates.

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 with no filler; the non-execution/non-charge statement is front-loaded in second position to clarify scope. The first sentence reads as a compact keyword list but remains efficient.

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 8-parameter tool with a nested object and no output schema, the description is thin. It does not explain what the preflight returns, how to supply the service input, or the meaning of most parameters, leaving substantial gaps 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% with 8 parameters (including a nested 'input' object). The description gestures at 'network' and 'budget' but never maps or explains any parameter, leaving serviceId, intentId, protocol, correlationId, idempotencyKey, and the nested input entirely undocumented.

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 function: a free service-specific preflight covering schema, network, budget and economic checks. It clarifies the scope and the non-executing nature, which helps distinguish it from phion_execute, though it does not explicitly name sibling tools.

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 rather than stated — 'It does not execute or charge' hints that this is a safe step before execution, but there is no explicit 'use before phion_execute' or 'when not to use' guidance. The agent must infer the 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description still adds genuine behavior: it preserves UNKNOWN, abstains when evidence is insufficient, and never authorizes payment or execution, which tells the agent how to interpret partial or missing results.

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 purpose, and every clause carries information (scope, constraint handling, uncertainty policy, safety boundary). No filler or restated name/title.

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 a deep nested constraint schema, an executionMode enum, no parameter descriptions, and no output schema, the description is far too thin. An agent cannot know what shape the resolution result takes or what each constraint field means from this text alone.

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 4 parameters, including a nested constraints object with 13 undocumented sub-fields. The description only alludes to 'constraints' generically and never explains task vs capability, the anyOf requirement, or the SHADOW/ADVISORY/PREFLIGHT executionMode enum, 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 specific action and scope: provider-neutral capability resolution across eligible payment rails, with constraints applied. It implicitly separates itself from phion_execute by declaring it never authorizes payment or execution, but it never names or contrasts with the sibling resolvers (phion_discover, phion_preflight, phion_get_service).

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: 'Advisory only: never authorizes payment or execution' tells the agent this is not the execution path, which hints that phion_execute handles that. However, there is no explicit when-to-use statement and no routing guidance versus phion_discover or phion_preflight.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully reasserts that nothing is selected or charged, but says nothing about result ordering, pagination, or how the canonical inventory changes between calls.

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, tightly front-loaded with the verb and scope, with zero filler. Every clause (canonical inventory, search facets, no-selection caveat) earns its place.

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 0% schema description coverage, the description should do more: it never conveys the shape of results (list of services with prices and capabilities?) or how 'limit' caps them. Adequate for routing, incomplete 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 coverage is 0%, so the description must carry the parameter burden. It maps its facets onto query, capability, protocol, and maxPrice ('maximum advertised price'), which is real added value, but leaves the 'limit' parameter unexplained and gives no syntax or combination semantics for the free-text query.

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 (Search) and resource (complete canonical PHION inventory), plus the facets that can be searched: task, capability, protocol, price. The phrase 'without selecting or charging' implicitly separates it from action-oriented siblings like phion_execute or phion_preflight, though no sibling is named.

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?

'Without selecting or charging' implies this is a pre-selection, discovery-only step, which hints at when to use it. However, it never names the alternative (e.g. phion_get_service for a known service, phion_execute to act) or states explicit exclusions, leaving the agent to infer.

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, idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds only 'Free', which is a useful pricing trait not covered by annotations, but it omits what verification actually checks, what an invalid receipt produces, and any return 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 single sentence is front-loaded and free of filler. However, its extreme brevity borders on under-specification for a tool with three parameters and no schema descriptions.

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 0% schema description coverage, the description should explain return semantics and parameter roles. It does not, leaving an agent unclear about what verification produces and how to use the optional parameters.

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 the description only hints at the required 'receipt' parameter via the phrase 'signed receipt'. It says nothing about the optional 'content' or 'sources' parameters, so it does not compensate for the undocumented 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?

States a specific verb ('verification') and resource ('PHION signed receipt'), and adds the pricing trait 'Free'. It does not explicitly differentiate itself from siblings such as phion_preflight or phion_resolve, 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?

The description gives no when-to-use guidance, prerequisites, or alternatives. An agent must infer usage entirely from the tool name and title, with no exclusions or context about when this is preferable to sibling tools.

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