Kitden

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description adds the non-obvious remediation path (local page, previews, backs up, can undo) and forbids a tempting workaround, which is genuine behavioral guidance. It does not add rate/limit or scoping caveats, but nothing is contradicted.

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 sentences, front-loaded with what the tool returns, then the optional parameter, then the constraint and its remedy. Dense but every sentence carries information; the final sentence is long but its remediation detail is worth the length.

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-value explanation is unnecessary, and annotations cover the safety profile. What remains missing is only the meaning of `project_path`; otherwise the description is sufficient for an agent to call this correctly and to route around the write limitation.

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 carries the burden. It compensates well for `kind` by enumerating the six valid values the schema does not (mcp_server, skill, plugin, hook, marketplace, instructions) and implies `name`, but `project_path` is never mentioned, leaving a third of the parameters undefined anywhere.

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?

"Explain one name: every definition across clients and scopes, which one loads in the project, and why" states a specific verb (explain), a specific resource (one named item), and the exact output shape (all definitions + resolution + rationale). This clearly separates it from the list-style siblings (show_setup, list_findings, list_projects) without needing to name them.

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 trigger context (one name, ambiguity about which definition wins) and a strong operational rule: do not edit client settings files, instead direct the developer to `kitden open`. It stops short of explicitly contrasting with siblings such as show_setup for a whole-configuration overview, so the when-not is partially inferred.

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 and non-destructive, so the safety profile is covered; the description still adds real value by explaining the intended remediation path (local page via `kitden open`, which previews, backs up and undoes) and by warning against the tempting workaround of hand-editing settings files. It could say more about output shape, but an output schema 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?

Purpose and finding categories are front-loaded, followed by the parameter default and then the read-only/anti-workaround guidance. Dense but every sentence carries information; the parenthetical tool description is the only slightly sprawling element.

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 covers return values, so the description need not define them, and the annotation set covers safety. Combined with the finding taxonomy and the remediation guidance, an agent has enough to call this correctly; only sibling routing and path format remain open.

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% for the single parameter, and the schema default is null with no explanation. The description usefully resolves that ambiguity by stating project_path defaults to the current folder. It still says nothing about accepted path forms (relative vs absolute) or what happens with an invalid project.

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 opens with a specific verb+resource ("List problems for a project") and enumerates the concrete finding categories: duplicates, cross-client folder loads, overrides, unknown states, untested versions, gateway-bypassing MCP servers. That is far beyond the bare name. It does not, however, contrast itself with siblings like explain_item or show_setup, 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?

It gives a default for project_path (current folder) and a strong negative instruction not to edit client settings files, redirecting to `kitden open`. But it never states when to prefer this over explain_item or show_setup, which is the core routing decision an agent faces among these siblings.

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=false, so the safety profile is covered. The description adds value beyond that by warning against editing settings files directly and pointing to `kitden open`, which previews, backs up, and can undo changes.

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, front-loaded with the core purpose, followed by the read-only constraint and the workaround guidance. Every sentence carries information, though the second sentence is somewhat dense.

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. The description covers purpose, read-only behavior, and the correct alternative for mutations, leaving little an agent would need to infer before calling it.

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 there is no parameter semantics to explain; the baseline for a parameterless tool is 4. The description correctly implies no input 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 states a specific verb ('List') and resource ('projects') and even enumerates the returned facets: which clients know each project and whether the folder still exists. It is clearly distinguishable from siblings like list_findings or show_setup, though it does not name them 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?

It gives a clear directive for the mutation case: do not edit client settings files, instead tell the developer to use the local page via `kitden open`. This is actionable when-to-use guidance, but it does not explicitly contrast with the sibling tools for read scenarios.

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 restating read-only adds little. The valuable additions are the enumeration of what is inspected and the workaround path (`kitden open`) that previews, backs up and undoes changes, which is behavior an agent could not infer from annotations alone.

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 sentences, front-loaded with purpose, then defaults, then safety/workaround guidance. Dense and mostly waste-free, though the final clause about previewing, backing up and undoing is slightly verbose for what it conveys.

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 no explanation, and the description covers scope, defaults, client vocabulary and the safety posture for a read-only inspection tool. Minor gaps (path format, whether project_path must exist) keep it from a 5.

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 schema does not even list enum values, yet the description supplies the accepted client values (claude_code, claude_desktop_code_tab, codex, cursor) and the default behavior of both parameters. This meaningfully compensates for an otherwise bare schema; only path format conventions remain unstated.

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+resource: it shows what each AI coding client loads for a project, and enumerates the resource kinds (MCP servers, skills, plugins, hooks, marketplaces, instruction files) plus the attributes returned (source, scope, on/off state). It is clear what the tool does, though it does not explicitly distinguish itself from siblings like explain_item or list_findings.

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 concrete when-to-use context via defaults (project_path defaults to the current folder, client defaults to all four clients) and an explicit when-NOT/alternative: don't edit client settings files, instead direct the developer to the local page via `kitden open`. It stops short of routing against the sibling tools, but the exclusionary guidance is clear.

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