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

Annotations already provide readOnlyHint, destructiveHint, and idempotentHint. The description adds 'Read-only' and 'safe' context, consistent with annotations, but doesn't add significant new behavioral details beyond that.

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 concise sentences, front-loaded with the main action. No redundant 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 description covers the core purpose and usage distinction, but lacks parameter explanations for a tool with zero schema coverage. Output schema exists but is not described.

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%, meaning no parameter descriptions. The description does not explain the 'path' or 'limit' parameters, so it fails to add meaning beyond the 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?

The description clearly states the tool lists files under an allowed local directory, and distinguishes it from search by noting it's read-only and safer.

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 explicitly guides when to use this tool over search ('safer than search when the user asks what files are visible'), though it doesn't cover all sibling distinctions.

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 indicate readOnly, destructive, idempotent. Description adds no additional behavioral traits (e.g., pagination via offset/limit, error handling, permission requirements).

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 sentences, each essential. First states purpose, second adds a critical usage condition. No fluff.

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?

Despite existing output schema, description omits parameter meanings (especially offset/limit), error scenarios, and path requirements. Minimal for a tool with 3 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?

With 0% schema description coverage, description must explain parameters. It does not mention path, offset, or limit at all, leaving the agent with no guidance beyond the 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?

'Read a local file' is a specific verb+resource. The condition 'use only when the user provides an explicit path' distinguishes it from sibling tools that list or search files.

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?

Clear condition to use only when user provides explicit path. Does not name alternatives like hermes_list_files, but condition is explicit enough to guide 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds 'Read-only' which is redundant. It provides some context about the 'target' parameter for filenames, but does not disclose behavior beyond annotations, such as what 'allowed' means or any restrictions on file access.

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 consists of two concise sentences that are front-loaded with the core purpose. It efficiently conveys the tool's action and a key parameter hint without unnecessary details. Minor improvement could be moving the 'Read-only' annotation to the first sentence.

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 5 parameters (only 1 required) and an output schema present, the description covers the basic purpose but lacks details about search semantics (e.g., pattern matching type), the difference between 'files' and 'path' targets, and how file_glob and limit affect results. It is minimally adequate but not fully complete for complex use 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 coverage of parameter descriptions is 0%, so the description must compensate. It only adds meaning for the 'target' parameter by suggesting values 'files' or 'path'. No explanation is given for parameters like pattern, path, file_glob, or limit, leaving the agent to rely solely on parameter names which may be ambiguous.

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 tool searches allowed local files on the Hermes machine, with a verb and resource. It also provides a hint about using target='files' or target='path' for filenames. It distinguishes from siblings like hermes_list_files and hermes_read_file, but could be more specific about the search mechanism (e.g., pattern matching, content search).

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 for searching files, but does not explicitly state when to use this tool versus alternatives like hermes_list_files for listing directories or hermes_read_file for reading contents. No explicit when-to-use or when-not-to-use guidance is provided, leaving the agent to infer based on the sibling tool names.

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 provide readOnlyHint, destructiveHint, idempotentHint. The description adds value by enumerating the specific test areas (host identity, auth, etc.), including 'write sandbox,' which implies non-destructive writes. This goes beyond annotations without contradicting them.

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 of 15 words efficiently conveys the tool's purpose and scope. Every word earns its place with no waste.

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 zero parameters, the presence of an output schema, and comprehensive annotations, the description provides complete context. It clearly states what the self-test covers, leaving no ambiguity about the tool's functionality.

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 are zero parameters, so the description does not need to add parameter meaning. Schema coverage is 100% (vacuously). The baseline of 4 is justified as no additional parameter info is 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 clearly states the tool runs a 'local bridge self-test' covering specific areas: host identity, auth, read roots, write sandbox, sensitive path blocking. The verb 'run' is specific, and the resource is the self-test, which is distinct from sibling tools like hermes_list_files.

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 explicit when-to-use or when-not-to-use guidance is provided. The purpose implies it is for verifying the bridge setup, but there are no alternatives mentioned or exclusions. Given the simplicity, a score of 3 is appropriate as the usage context is implied.

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, destructiveHint, idempotentHint, and openWorldHint. The description adds value by explicitly stating that tokens are not revealed, which is a critical security context beyond 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 extremely concise with two sentences that front-load the purpose ('Show'). Every sentence adds value, with no unnecessary 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?

Given that there is an output schema and the description lists exactly what the tool shows, the description is complete for a read-only config display tool. No additional context is needed.

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 are no parameters, and schema coverage is 100% (trivially). The baseline for 0 parameters is 4, and the description does not need to add parameter info.

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 tool shows configuration information including specific aspects like identity, read roots, write sandbox, auth status, and safety modes. It also specifies what it does NOT reveal (tokens), distinguishing it from sibling tools that deal with files or other operations.

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 does not explicitly state when to use this tool versus alternatives. Usage is implied as inspecting server configuration, but there is no guidance on scenarios or 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=true, destructiveHint=false, idempotentHint=true. The description adds 'safe for a connector smoke test' which reinforces but does not significantly extend behavioral insight beyond 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 consists of two succinct sentences with no fluff, conveying purpose and safety concisely.

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 no parameters, rich annotations, and an output schema (presumed), this description is complete enough. It tells the agent exactly what the tool does and that it's safe to use.

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 input schema has zero parameters, so the description does not need to explain parameters. It nonetheless adds value by specifying what is listed ('installed Hermes skills'), providing context beyond the empty 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?

The description clearly states the action ('List'), the resource ('installed Hermes skills'), and scope ('on this machine'). It distinguishes from sibling tools like hermes_skill_view (which likely shows a specific skill) and hermes_list_files (different resource type).

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 explicitly recommends use as a 'connector smoke test' implying it's safe and suitable for verifying connectivity. It does not specify when not to use it, but the safe nature is clear.

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, destructiveHint, and idempotentHint. The description adds 'Read-only' which is redundant. It discloses no additional behavioral traits (e.g., behavior for missing skill, rate limits, or output details).

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 extremely concise: two short sentences with no unnecessary words. Every part is purposeful.

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 output schema exists and the tool has only one parameter, the description is largely complete. However, it could briefly mention that the content is specific to a skill's SKILL.md file, which is implied but not explicit.

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 only parameter 'name' has no schema description (0% coverage). The description says 'by name' but does not clarify format, case sensitivity, or provide examples. Minimal value added beyond the 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?

The description clearly states the action ('Read'), the specific resource ('SKILL.md content for one installed Hermes skill by name'), and implicitly distinguishes from sibling tools like hermes_skill_list (which lists skills) and hermes_read_file (which reads arbitrary files).

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 by focusing on a specific resource ('by name'), but provides no explicit guidance on when to use this tool versus alternatives (e.g., hermes_skill_list for listing skills, hermes_read_file for other files). Minimal context for 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?

Adds 'read-only' and 'safer' beyond annotations (which already mark readOnlyHint=true and destructiveHint=false), reinforcing behavior without contradiction.

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 front-loaded sentences deliver purpose and key attribute concisely, with no unnecessary 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?

Simple tool with output schema and annotations; description covers core purpose but omits parameter details, which are essential for usage completeness.

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?

No parameter descriptions in schema or description; 'shallow' hints at depth but does not explain path, depth, or limit semantics, failing to compensate for 0% schema coverage.

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?

Description uses specific verb 'show' and resource 'shallow directory tree', clearly distinguishing from sibling tools like regex-based search.

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?

Suggests use for discovery over regex search; implies read-only nature. No explicit when-not-to-use, but context with sibling names provides guidance.

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, destructiveHint=false, and idempotentHint=true, which the description's 'View' aligns with. The description adds useful context: images must be 'allowed local' files, and it specifies supported formats, enhancing transparency beyond 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 a single sentence that immediately states the action ('View'), the resource ('allowed local image file'), and the context ('design review'). No wasted words; front-loaded and 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 a simple tool with one parameter, an output schema, and no nested objects, the description adequately covers purpose and usage. It specifies file formats and the 'allowed' constraint, though parameter details are missing, slightly reducing completeness.

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 only parameter is 'path' (required, string). The schema has 0% description coverage, so the description should provide context. However, the description does not explain the 'path' parameter, its expected format, or examples, leaving the agent to infer meaning from minimal info.

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 tool's function: viewing an allowed local image file as image content. It specifies supported formats (PNG/JPEG/WebP/GIF) and distinguishes from sibling tools like hermes_read_file (text reading) and hermes_list_files (listing files).

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 indicates when to use the tool: for image viewing of allowed local files during design review. It does not explicitly mention when not to use it or suggest alternatives, but the context of sibling tools makes the intended use clear.

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