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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description only restates the return content, which the output schema already documents, and adds no behavioral context such as auth requirements, side effects, or scope limits.

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 no filler; every word maps to the tool's purpose.

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 0-param read tool with full annotation coverage and an output schema, the description is minimally sufficient. It is somewhat thin on when to choose it over the sibling readers, but the structured fields carry most of the burden.

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, which per the rubric establishes a baseline of 4. There is nothing for the description to clarify on the input side.

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 gives a specific verb ('Return') and enumerates the resources returned (configured sources, source states, Capalith features), so the agent knows it reads configuration. It does not, however, distinguish this tool from siblings like 'inspect' or 'discover', leaving overlap ambiguous.

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 the siblings (inspect, discover, traverse, index_skills), nor any exclusions, prerequisites, or triggering conditions. The agent is left to infer usage entirely.

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 readOnlyHint=false, so the description's 'Writes only Capalith's catalog, never sources or host settings' is essential and non-obvious context explaining the write. It also states it 'does not load or activate skills,' bounding side effects, and explains snapshot vs. refresh 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?

Front-loaded with purpose, then state/side-effect constraints in compact sentences. It is dense and mostly earns its space, with minor redundancy between the snapshot and refresh sentences.

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 exists, so return values need not be explained, and the description covers the stateful behaviors (catalog preparation, snapshot reuse, refresh) an agent must know. It is complete for a 9-parameter search tool, though pagination semantics could be slightly clearer.

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 100% schema coverage the baseline is 3, and the description adds real meaning beyond the schema: workspace and host_homes select task/profile context when it differs from the server, and extra_source_paths is described as replacing previous additions. view_id pagination usage is only lightly covered, keeping this at 4.

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 ('Search Agent Skills by task') and clarifies scope ('including known skills and declared relationships'). It also distinguishes itself from the sibling index_skills by naming it directly, so an agent can route correctly without opening schemas.

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 context: the first search builds the catalog, repeated searches read the snapshot, and index_skills is the explicit refresh path. It lacks an explicit when-not-to-use statement (e.g., versus inspect or traverse), but the index_skills routing is concrete.

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 annotations declaring readOnlyHint=false but destructiveHint=false, the description resolves the ambiguity: 'Creates Capalith's catalog, never edits sources or activates skills.' That tells the agent exactly what side effect occurs and what does not, which the annotations alone cannot convey. It does not mention failure modes or 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?

Front-loaded with the core action, then compact clauses for each parameter's behavior. Dense but every sentence carries a distinct instruction; the 'config_show previews roots' aside is slightly tacked-on but still useful routing 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 tool mutates its own catalog, and the description states the boundary (creates catalog, never edits sources/activates skills) plus the parameter interplays. An output schema exists, so return values need not be explained. Minor gap: no mention of what happens to previously indexed skills on refresh.

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 100%, so the baseline is 3, but the description adds real meaning: no-arg calls refresh, source_paths is restricted to explicit roots, and host_homes should come from known host context when the environment omitted a value. This clarifies the interaction between optional parameters beyond the per-field schema text.

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?

Opens with a specific verb+resource: 'Find and index installed Codex, Claude Code and current Hermes profile skill directories.' It also distinguishes itself from a sibling by noting 'config_show previews roots,' so an agent can separate indexing from previewing. It stops short of fully differentiating from discover/inspect/traverse, so not 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?

Explicitly states the invocation modes: no-argument calls refresh the selection, source_paths selects only explicit custom roots, and host_homes is supplied 'from known host context if the client's environment omitted a custom home.' It also notes first-use setup is handled by 'discover.' Clear context with no explicit when-not guidance beyond that.

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 and openWorldHint=false, so the safety profile is covered and the description is consistent with it. The description adds the three return modes, which is genuinely useful behavior information, but says nothing about auth requirements, rate limits, or error conditions. Some added value beyond annotations, but not rich.

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 no wasted words that enumerates the three return modes. Efficient, though the extreme terseness leaves the mode-selection logic unstated rather than merely brief.

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 a full output schema present, the description need not explain return values, and annotations cover the read-only/safety profile. Combined with 100% parameter coverage, the definition is adequate for an agent to call this correctly. The one real gap — routing between this and its siblings — is minor given the structured data available.

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 artifact_id, resource_path, and content_digest are all documented in the schema itself. The description reinforces the artifact-version scoping but adds no syntax, format, or meaning beyond what the schema already provides. Baseline 3 applies when the schema carries the load.

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 resource scope — stored metadata, a resource list, or one resource for an artifact version — so an agent knows what data comes back. It does not, however, explicitly position itself against siblings like discover or traverse, leaving the reader to infer the boundary. Clear but without sibling differentiation.

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 or when-not-to-use guidance and no mention of alternatives among discover, traverse, config_show, or index_skills. The only selection cue (omit resource_path vs. supply it) lives in the input schema, not the description. No usage guidance beyond the bare purpose.

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 and openWorldHint=false, so safety is covered. The description's only behavioral contribution is the qualifier 'declared' relationships, which usefully implies these are explicitly asserted rather than inferred links, but it says nothing about how depth, direction, or pagination affect the result.

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 with the action and resource and contains no filler. It is arguably too terse for a 9-parameter traversal tool, but measured purely as conciseness and structure it is clean 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?

An output schema and annotations exist, so safety and return shape need not be restated. However, for a traversal tool with depth, direction, view-based pagination, and source prioritization, one sentence leaves the agent without context on traversal semantics or paging behavior.

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 every parameter (depth, view_id, direction, source_ids, etc.) is already documented in the schema. The prose description adds no syntax or constraint detail beyond that, so the 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?

The description gives a specific verb ('Return') and resource ('declared relationships') scoped to 'an artifact version,' so the agent knows exactly what operation this is. It does not, however, distinguish this traversal operation from siblings like inspect or discover, which likely also read artifact metadata.

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 choose traverse over the sibling tools, nor any stated preconditions (e.g., that artifact_id/content_digest must come from a prior Capalith call). The word 'declared' hints at a scope boundary but is not framed as usage guidance.

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