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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds a small amount of context with 'public' and 'discovered', but it does not disclose behavior for unknown actions, error cases, or the expected return shape beyond 'schema'.

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 conveys the verb, resource, and scope efficiently, which is appropriate for such a simple read-only lookup 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 one-parameter read-only tool, the description is minimally adequate given the annotations. However, because there is no output schema and parameter coverage is 0%, the description leaves the agent to infer important details about how to obtain an action name and what the returned schema looks like.

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 should compensate by explaining the meaning of the action parameter, but it does not. The qualifier 'public' hints at a constraint on valid actions, but the description does not state that action must be a discovered action name or explain how it relates to sibling tools.

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: return a discovered schema for a public Exact action. It is clear about the resource type (action schema) and naturally distinguishes from sibling tools like exact_list_actions or exact_get_entity_schema, though it does not explicitly call out those alternatives.

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 about when to use this tool versus the sibling tools, no mention of needing an action name from exact_list_actions, and no explanation of when it would be inappropriate. The agent must infer usage entirely from the tool name and sibling 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds a small behavioral nuance by saying capabilities are 'detected or verified,' which implies active checking rather than a static lookup, but it does not elaborate on what detection/verification entails or what failure states might occur.

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 delivers the core purpose immediately and earns every word.

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-parameter, read-only, idempotent introspection tool with rich annotations, the description is largely sufficient. It could be slightly more complete by describing the shape or semantics of the returned capabilities, especially since there is no output schema, but the current level is adequate for an agent to understand the tool's role.

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 has zero parameters and the schema is empty, so parameter semantics are effectively not applicable. The baseline for a no-parameter tool is 4, and the description correctly makes no parameter claims.

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 ('Return') and a clear resource ('capabilities detected or verified against the configured Exact installation'). This distinguishes it from the sibling tools, which focus on server info, entities, actions, schemas, and records. The phrase 'detected or verified' adds useful specificity beyond a generic 'get capabilities'.

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 implies the tool is used when an agent needs to know what capabilities the Exact installation supports. However, it does not explicitly state when to use this tool versus alternatives like exact_get_server_info or exact_list_actions, nor does it mention any 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description is not the sole carrier of safety information. It adds some useful context with 'allowed' and 'validated', hinting at access restrictions and key requirements, but does not disclose error behavior or what happens when a record is not found.

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, tightly written sentence with the verb and core resource front-loaded. There is no filler or redundant detail; every word contributes to identifying the operation.

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 no property descriptions in the input schema, the description is too thin to fully support correct invocation. It omits how entity values are determined, what select controls, what validation means in practice, and how this tool relates to sibling read tools.

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 only addresses the 'key' parameter ('validated simple or composite key'). The 'entity' and 'select' parameters are not explained at all, leaving the agent to infer their meaning from names alone.

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 clear verb ('Read'), a specific resource ('one allowed entity record'), and a distinguishing mechanism ('validated simple or composite key'). It effectively separates this from list/schema siblings by emphasizing a single record, though it does not explicitly name any sibling.

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 phrase 'Read one allowed entity record by a validated simple or composite key' implies the tool is for fetching a single record when a valid key is available. However, it gives no explicit guidance on when not to use it or when to prefer siblings like exact_list_entity_records or exact_get_entity_schema.

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=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds mild behavioral context via 'discovered support' and 'allowed entity,' but it does not explain what 'discovered support' means, how discovery happens, or what the response 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?

The description is a single, efficient sentence that front-loads the core action and output categories. There is no filler or redundancy, and every word contributes meaning.

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 read-only, idempotent introspection tool with one parameter, the description is adequate but not complete. It names the output categories but does not define 'discovered support' or clarify how the entity parameter should be specified, leaving some ambiguity despite helpful sibling names like exact_list_entities.

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 for the single required 'entity' parameter. It only adds the phrase 'allowed entity,' which gives a minimal constraint but does not explain what values are valid, how they are formatted, or where the allowed list can be obtained.

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 the verb 'Return' and the resource ('keys, properties, types, and discovered support for an allowed entity'). It is distinguishable from siblings like exact_get_entity, which would return actual entity data rather than its schema, though it does not explicitly name that sibling.

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 guidance is given about when to use this tool versus alternatives such as exact_list_entities or exact_get_action_schema. There are no explicit conditions, prerequisites, or exclusions, so the agent must infer usage from the tool name and sibling 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 read-only, idempotent, and non-destructive behavior. The description adds value beyond those by stating that connection secrets are not exposed and that metadata availability is checked live, which is useful behavioral context not present in the annotations. No contradiction 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 one efficient sentence that front-loads the core purpose and includes an important safety constraint. There is no redundant wording, and every phrase adds meaning.

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 tool is simple (one optional parameter) and annotations cover safety traits, but there is no output schema and the description does not clarify the return structure or the refresh parameter's effect. The description is adequate for basic invocation but incomplete for a fully informed agent.

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 the single 'refresh' parameter, but it never mentions it. The boolean name and default value give minimal hints, but the agent is left without guidance on what refresh does, when to enable it, or the consequences of leaving it false.

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 uses a specific verb ('Check') and identifies the resource as server info, then enumerates the checked aspects: configuration, connectivity, product selection, and live metadata availability. This clearly separates it from sibling tools that focus on capabilities, entities, or actions. 'Product selection' is slightly ambiguous, which prevents a top score.

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 implies the tool is the diagnostic entry point for server-level concerns, but it provides no explicit when-to-use guidance and does not mention alternatives such as exact_get_capabilities or exact_list_entities. An agent must infer routing from the list of checks rather than being told directly.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds useful behavioral context about live metadata discovery and exclusion of internal-looking actions, but does not disclose return format, pagination, or how the optional search parameter affects 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?

A single, tightly worded sentence that front-loads the core purpose and adds the key exclusion rule. Every word contributes value, with no redundancy or filler.

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 one optional parameter, no output schema, and no parameter descriptions, the description is too thin. It omits what the returned list looks like, how the search parameter interacts with the listing, and what qualifies as 'internal-looking,' which an agent would need for confident 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%, and the description does not explain the 'search' parameter at all. While the parameter name suggests it filters results, the agent is left without information on whether it is a substring, prefix, exact match, or applies to action names only.

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 ('List'), a clear resource ('public actions discovered in live Exact metadata'), and an explicit exclusion ('internal-looking actions are excluded'). This clearly distinguishes it from siblings like exact_get_action_schema, which retrieves schemas for specific actions rather than listing actions.

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 conveys the scope and filtering behavior of the tool, making it clear it is for enumerating public actions rather than inspecting a single action's schema. However, it does not explicitly name sibling tools or provide when-to-use versus when-not-to-use guidance, leaving some inference to 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond these by disclosing that results are 'live' and constrained by the 'effective read policy', which informs the agent that the returned set may vary based on current permissions.

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 wasted words. Every element—'List', 'live metadata entities', and 'allowed by the effective read policy'—earns its place and collectively conveys the tool's core behavior.

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 simple list tool with one optional parameter and no output schema, the description covers the main purpose and policy filtering. However, it omits any guidance on the 'search' parameter and says nothing about the shape or paging of the returned entity list, which an agent may need for correct invocation and interpretation.

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 needed to explain the optional 'search' parameter but does not mention it at all. The parameter name is self-explanatory to some degree, but the description adds no meaning beyond the schema, leaving the agent to guess how search interacts with the 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 uses a specific verb ('List') and resource ('live metadata entities'), and adds a meaningful scope qualifier ('allowed by the effective read policy'). This clearly differentiates it from siblings like exact_get_entity (single entity retrieval), exact_get_entity_schema (schema retrieval), and exact_list_entity_records (records within an entity).

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 implies the tool is used for enumerating metadata entities, and the 'allowed by the effective read policy' qualifier hints at its filtering behavior. However, it provides no explicit guidance about when to choose this tool over siblings such as exact_list_actions or exact_list_entity_records, nor does it state any 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?

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds meaningful context beyond those: only 'allowed' records are accessible, fields are validated, a safe continuation cursor is provided, and raw OData is not accepted. This enriches the agent's understanding without contradicting 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?

The description is two sentences, front-loaded with the action and resource, and every clause adds useful information. There is no fluff or repetition.

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 tool's high parameter complexity and lack of an output schema, the description provides a solid high-level map but omits details such as valid entity names, select-field semantics, cursor/skip interplay, and explicit sibling differentiation. Annotations reduce the safety burden, but the description is not fully complete for a first-time caller.

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 for missing parameter explanations. It adds semantic meaning for filters, ordering, limits, and cursor-based continuation, and clarifies that filters are structured rather than raw OData. However, it does not explicitly describe the 'entity' or 'select' parameters, leaving those to inference.

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 the action ('Read'), the resource ('entity records'), and the key capabilities: structured filters, validated fields, ordering, limits, and a continuation cursor. This distinguishes it from sibling metadata tools like exact_list_entities or exact_get_entity_schema. However, it does not explicitly name a sibling alternative such as exact_get_entity, so it stops short of a perfect 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 implies usage: call this when you need to read permitted entity records with filtering and pagination. It does not explicitly state when to prefer a sibling tool, nor does it provide alternatives beyond the rejection of raw OData.

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