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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely useful data-quality context beyond that — that entries carry official doc links, a per-entry verification date, and that 'unknown' explicitly means the official docs are silent. This tells the agent how much to trust a given cell, which is the kind of disclosure annotations cannot carry.

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 with no filler, and the coverage list is front-loaded before the 'unknown' caveat. Minor deduction because it opens with a dependent clause ('Where ... read ...') instead of a subject, making the first read slightly less immediately scannable.

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 lookup with no output schema, the description does the necessary work: it enumerates the agents and config categories covered and hints at the record shape (doc link + verified date) plus the 'unknown' sentinel. A small gap remains around whether it returns a flat table vs. per-agent nesting, but nothing blocking 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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It does not need to explain argument behavior at all.

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 the exact resource — a cross-agent matrix of where Claude Code, Codex CLI, Cursor and Gemini CLI read instructions, MCP config and skills — which is concrete enough to distinguish it from convert_* and detect_agent_configs. It lacks an explicit verb ('Look up...'), so the agent must infer this is a read-only reference rather than an action.

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: the content (doc links, verification dates) signals a static reference to consult before writing or converting config. Nothing says when to prefer this over sibling tools like detect_agent_configs (which presumably probes the local machine) or convert_mcp_config, leaving the agent to reason about the boundary itself.

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 no annotations, the description carries the full burden and does supply the critical trait: 'Returns target files; writes nothing' — a genuine non-destructive guarantee an agent cannot infer from schema. It stops short of describing failure behavior for malformed input or how 'auto' detection resolves ambiguity.

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, no filler; the conversion scope comes first and the non-writing guarantee is placed as a trailing, high-salience clause. Every phrase carries 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?

For a 3-parameter, no-output-schema tool the description covers input forms, output behavior, and target set — enough to invoke correctly. Gaps remain around the 'auto' format resolution and validation errors, but nothing essential 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 only 33% (only 'text' is documented), so the description must compensate — and it does, mapping 'mcpServers JSON or Codex TOML' to `text`/`format` and naming Claude Code/Desktop, Cursor, Gemini CLI, and Codex as the `targets` values. It does not explain the 'auto' enum value or the default-all-targets behavior, keeping it below 5.

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 ('Convert') and resource ('MCP server definitions') and enumerates the exact source/target format pairs (mcpServers JSON, Gemini httpUrl/url, Codex [mcp_servers.*]). An agent can tell this apart from convert_rules or migrate_project without opening a schema.

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 format-pair enumeration implies when the tool applies, and 'writes nothing' implicitly distinguishes it from a migration tool. However, there is no explicit when-to-use/when-not statement or named alternative among the siblings (convert_rules, detect_agent_configs, migrate_project).

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 no annotations, the description carries the burden and does well: it discloses the return shape ('file paths + contents and a shell command') and, importantly, that it 'writes nothing' — a non-destructive, preview-style operation. It doesn't clarify whether the generated shell command is what actually performs the symlink/import side effect, which is the one residual ambiguity.

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 dense sentences, front-loaded with the conversion scope and closed with the output/write behavior. Every clause carries information; nothing is wasted.

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?

No output schema exists, and the description compensates by describing the return payload and the no-write guarantee. A reader can call it correctly; only the interaction between the link parameter and the returned shell command is left to inference.

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 75%, with descriptions on text, source, and link, and an enum that makes targets self-evident. The description adds nothing parameter-level (no explanation of when to pick link=symlink vs import, and no description for targets); baseline 3 is appropriate given the schema does the heavy lifting.

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 ('Convert') and resource ('agent instructions') and enumerates the concrete source file formats (CLAUDE.md, AGENTS.md, .mdc rules, .cursorrules, GEMINI.md) and target tools. This clearly separates it from convert_mcp_config (config, not instruction files) and from detect_agent_configs.

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: the enumeration of source formats makes it obvious when the tool applies, but there is no explicit 'use this when / don't use this when' and no mention of the sibling tools (e.g. detect_agent_configs to find the files first). The 'writes nothing' clause hints at a dry-run workflow but doesn't state it as 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?

The readOnlyHint annotation already declares the safe read-only behavior, and the description reinforces that while adding the scan scope. However, it does not disclose recursion behavior, handling of missing directories, symlink behavior, or whether all matches are returned, so the added behavioral context is limited.

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 definition is a single front-loaded sentence with no wasted words. The list of target files is dense but directly supports 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 one-parameter read-only detection tool, the description is sufficient to call the tool, but it does not explain the return shape or whether scanning is recursive. Since there is no output schema, return semantics remain ambiguous.

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%, and the single parameter is documented as the absolute path of the project root. The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate.

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, "Scan," and a specific resource, a project directory, plus enumerates the exact config files and folders it detects. An agent can distinguish this discovery operation from conversion, migration, and compatibility siblings.

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 states that the scan is read-only and what it looks for, but gives no explicit guidance on when to use it versus convert_rules, convert_mcp_config, migrate_project, or compat_matrix. It does not mention prerequisites, exclusions, or recommended sequencing such as scanning before migration.

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?

Goes well beyond the destructiveHint annotation by disclosing that the default is a dry run returning a plan, that files are only touched when write=true, that existing files are skipped unless overwrite=true, and that Gemini settings.json is merged rather than replaced. That is exactly the behavioral context an agent needs before a potentially destructive call.

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 action and immediately followed by the safety-critical default. Every clause carries information; nothing is padded.

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 destructive-by-annotation mutation tool with no output schema, the description covers the essential safety contract and the merge edge case. Remaining gaps are the unexplained link/source semantics and no signal about what the returned plan 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 coverage is only 33%, yet the description explains write and overwrite thoroughly and flags the merge exception. However, the 'link' parameter (none/symlink/import) and 'from' source selection get no explanation in either schema or description, leaving real gaps.

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: generate target-tool config files from the project's existing instructions and MCP config. That is clearly a whole-project migration, distinct from the narrower feel of convert_rules or convert_mcp_config, but the description never names those siblings to confirm 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?

Usage is implied by the dry-run-by-default framing (call it to preview a migration), but there is no explicit when-to-use-this-vs-alternatives guidance despite three plausible sibling tools. The write/overwrite conditions describe safe invocation rather than tool selection.

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