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

No annotations are supplied, so the description carries the full burden, and it discloses genuinely useful behavior: the server ships no skill files, only working-directory installs are readable, and a missing skill produces an error containing installation guidance rather than an empty result. It does not mention read-only safety, permissions, or return size, but for a simple retrieval tool the disclosure is solid.

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 resource, followed by the failure contract. Every clause carries information and 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 one-parameter read tool with no output schema, the description covers what is returned (the SKILL.md text), where it comes from, and what happens on failure. The only minor gap is that it does not state the response form (raw markdown vs. structured wrapper), though 'Return the SKILL.md' largely implies 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds meaning beyond the schema by explaining that skill_id maps to a directory name resolved under two possible install roots, and the 'do not invent' clause clarifies that the ID must correspond to a real installed skill.

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 and resource ('Return the SKILL.md of a Fredo QA skill') and even names the resolution locations (skills/<id>/ or .agents/skills/<id>/), which distinguishes it from list_skills, install_skill and the other siblings without opening the 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?

It gives clear when-to-use context by scoping the call to already-installed skills and adds a when-not/fallback condition: if the skill is not installed the call fails with installation instructions, so the caller should not fabricate rules. It stops short of explicitly routing the agent to install_skill or list_skills to discover valid IDs, which would have made this a 5.

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?

No annotations are supplied, so the description carries the full disclosure burden. "Retrieve" implies a non-mutating read and the sentence lists the categories of data returned, which is useful, but it says nothing about whether the call is local or remote, whether it requires a license key or auth, or whether results are cached — all plausible concerns given the licensing siblings.

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, hedging, or repetition. Every clause (version, protocol specification, runtime metadata) carries distinct information about the return content.

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 annotations, the description compensates by enumerating what the response contains, which is the main thing an agent needs. Minor gaps remain around auth/licensing requirements and whether the call has side effects, but for a zero-param metadata read this is close to sufficient.

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 schema leaves nothing to explain and the baseline is 4. The description correctly adds no parameter discussion, avoiding noise.

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 ("Retrieve") and enumerates the concrete resources returned: active package version, protocol specification, and runtime metadata of the Fredo QA MCP Server. This is clearly distinguishable from the sibling tools, which all deal with skills or licensing, though the description never names those siblings to make the contrast explicit.

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: an agent can infer this is the discovery/metadata call to make before other operations, but there is no explicit when-to-use statement, no prerequisites, and no mention of alternatives. For a zero-parameter read tool the inference is easy, but the description does no active work here.

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 well: it discloses that files are written to disk, that confirm: true is required, that the default returns a preview with no filesystem changes, and the precise failure mode when no source skill exists. It does not cover overwrite/idempotency behavior for an already-installed skill, nor the role of license_key, which leaves some mutation semantics unexplained.

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 dense sentence pair that front-loads the install action, then the artifact layout, then the confirmation requirement. It is efficient with no filler, though the nested parentheticals make it harder to scan than shorter, separated sentences would.

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 4-parameter mutation tool with no output schema and no annotations, the description covers the key facts an agent needs: destination, source lookup, fail condition, and the preview-vs-write gate. Gaps remain around overwrite behavior on re-install and the license_key parameter, both of which matter for a disk-writing tool.

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 all four parameters already have descriptions, establishing the baseline of 3. The description reinforces confirm's write-gate semantics but adds nothing about license_key (optional signed license path/JSON) or project_path, and the skill_id source-resolution path is only partly explained 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 names a specific verb and resource ("Install a Fredo QA skill") and pins down the exact destination (.agents/skills/<skill_id>/ with SKILL.md and LICENSE), the source of the copied file, and the failure condition. This clearly separates it from siblings like list_skills, get_skill_rules, and sync_workspace_skills, which do not write a new skill directory.

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 concrete when-to-use context: a skill source must already exist in skills/<id>/ or .agents/skills/<id>/, otherwise the call fails, and confirm must be true to write. It stops short of explicitly routing the agent to alternatives such as sync_workspace_skills for bulk syncing or list_skills for discovery, but the preconditions are 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?

No annotations are provided, so the description carries the full burden. It does disclose a meaningful trait: results are scoped by the current license tier (Free, Pro, Enterprise), which an agent would not otherwise know. It does not state that the operation is read-only, note any pagination/result-size behavior, or mention auth/license prerequisites beyond the tier mention.

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 sentence, front-loaded with the action and resource. Every clause (license tier scope, rule summaries, categories) contributes information; nothing is redundant or 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 low-complexity list tool with one optional, fully documented parameter and no output schema, the description covers purpose, scope, and a rough sense of return content. Minor gaps remain around return structure (e.g., ordering, whether full rule text is included) and read-only status, but nothing an agent needs in order to call it correctly 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 description coverage is 100% and the single optional 'category' parameter is fully enumerated in the schema (core, language, quality, compliance, enterprise). The description mentions 'categories' but adds no filtering semantics or format detail beyond what the schema already provides, so the baseline of 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 uses a specific verb and resource ('List all Fredo QA Skills') and adds scope (current license tier) plus the shape of the result (rule summaries and categories). This distinguishes it from siblings like get_skill_rules or install_skill, though it never names an alternative 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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The use case is only implied: browse available skills, presumably before calling install_skill or get_skill_rules. Adequate but leaves the agent to infer routing.

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 supplied, the description carries the full burden and does well: it states files are moved not deleted, that they remain fully recoverable in .agents/.archive/, and that the default run is a read-only preview. Gaps remain around whether the archive can be restored through any tool, what happens on name collisions, and how 'detected project tech stacks' determines candidates.

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 the action and destination, then safety, then the confirmation requirement — a logical order an agent can scan quickly. There is mild redundancy between 'Safely prunes' and 'Non-destructive', but no sentence 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?

For a mutation tool with zero annotations and no output schema, the description covers the essentials: what is moved where, recoverability, and the dry-run-by-default contract. It does not describe the shape of the preview response or the interaction with keep_skills, which an agent would need to interpret results fully.

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 the schema already explains confirm, keep_skills, and project_path, making 3 the baseline. The description reinforces the confirm default-to-preview behavior but never mentions keep_skills, the one parameter whose override semantics (pinning skills not auto-detected) would benefit from narrative explanation.

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 and resource ('prunes ... QA skills from .agents/skills/') plus the exact mechanism ('archiving them to .agents/.archive/'). That distinguishes it immediately from siblings like list_skills, install_skill, and sync_workspace_skills, which read, add, or sync rather than remove.

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 operational context: a preview is returned unless the caller sets confirm: true, so the safe default path is spelled out. It stops short of naming alternatives (e.g. use list_skills to inspect candidates before pruning) or stating when pruning should not be attempted.

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 supplied, the description carries the burden and does well: it discloses that traversal only happens on confirm, that the default is a non-scanning preview, that it is 'sub-second', and that a user agreement gate exists. It stops short of stating that nothing is written to disk or how results are reported, which for a filesystem-touching tool is a meaningful omission.

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 does and what it verifies, then the gating rule. The confirm/default behavior is restated in both prose and schema, a small redundancy, but overall the text is dense and earns its 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?

For a two-parameter read-out tool with no output schema, the description should indicate what a confirmed run returns (a report object? findings list? pass/fail per check?). It only describes the preview mode's output, leaving the actual audit result shape unspecified.

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% and both parameters are documented there, so the description's explanation of confirm:true vs false largely duplicates the schema text. The added phrasing 'requires user agreement' frames confirm as a consent gate rather than a plain flag, which is mild extra value; project_path gets no elaboration 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 names a specific verb and resource ('preflight check ... repository stack, governance policies, and baseline scaffolding') and enumerates exactly what is verified: AGENTS.md, licensing, .gitignore secret hygiene, dependency lockfile, and test runner declaration. Nothing among the siblings (skills, license, version tools) overlaps, so an agent can place it immediately.

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 triggering condition — run it 'before modifying code' — which is real situational guidance rather than a restatement of the name. It lacks an explicit when-not or a named alternative, but the sibling tools are unrelated utility calls, so the practical gap is small.

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?

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses that the key is session-scoped and that the file must be signed, but it does not say what happens on an invalid/expired license (error vs. silent no-op), whether an existing key is replaced, or whether the setting persists beyond the session.

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; the scope ("active session") and outcome ("unlock Pro or Enterprise skills") are stated efficiently. Slightly dense phrasing but 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?

For a one-parameter tool with no output schema, the description covers purpose and effect adequately. However, it omits failure behavior and confirmation of what a successful call yields, which an agent would need to handle bad licenses correctly.

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% and the single parameter is already well documented in the schema as a path to license.json or its raw JSON content. The description adds no further meaning about accepted formats or precedence, so the schema baseline of 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 pairs a specific verb ("Set") with a specific resource ("signed ... license file") and states the effect ("unlock Pro or Enterprise skills"). That distinguishes it well from the sibling verify_license, though the distinction is implied by the verb rather than stated 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?

"for the active session" hints at when this applies (session-scoped activation before using Pro/Enterprise skills), but there is no explicit when-to-use versus verify_license guidance and no stated prerequisites such as needing a valid signed file first. Usage is inferable but not spelled out.

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 write target (.agents/skills/), the safe dry-run default, and the explicit confirmation requirement before any filesystem mutation, plus that license provisioning is part of the operation. It still omits what happens to already-installed skills (overwrite/skip/merge) and whether license validation must succeed first.

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 with no waste: the first establishes what the tool does and where it writes, the second front-loads the safety-critical confirmation behavior. Nothing is repeated or 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 mutation tool with no annotations and no output schema, the description covers the most important unknown: that writes are gated by confirm and default to a preview. Remaining gaps (idempotency, existing-skill handling, what the dry-run preview contains) are real but secondary.

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 all four parameters are already documented in the input schema. The description restates the confirm/confirm:false semantics rather than adding new meaning about skills, license_key, or project_path, so 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?

States a specific verb and resource: auto-detects the project stack and provisions matching QA skills and licenses into .agents/skills/. It is clear what the tool produces and where it writes, but it never distinguishes itself from siblings like install_skill or prune_skills, so an agent must infer the difference.

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 through the auto-detect behavior (omitting skills) and the confirm gate, but there is no explicit statement of when to choose this over install_skill, list_skills, or set_license_key, and no prerequisites are given.

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?

No annotations are supplied, so the description carries the full burden. It usefully discloses the reported facets (including a non-obvious 'fallback status'), which effectively describes the return payload absent an output schema, but it never states explicitly that the call is side-effect free, what happens when no license is installed or the license is invalid/expired, or how errors surface.

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; the field enumeration is dense but every item conveys real information. Slightly list-like, but 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?

For a simple, zero-required-parameter inspection tool with no output schema, enumerating the reported values covers most of what an agent needs. The remaining gaps are edge-case behavior (no license present, invalid signature) and the omitted-parameter default, which are modest given the tool's simplicity.

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% and the single optional license_key parameter is fully documented there, including the 'without modifying session state' nuance. The description adds no meaning about the parameter and does not clarify the default behavior when it is omitted (i.e. inspecting the active session license).

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 (Inspect) and resource (the current Fredo QA license), and enumerates exactly what facets are reported: signature validity, tier, licensee, updates_until, and fallback status. This clearly separates it from the mutating sibling set_license_key.

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 word 'Inspect' suggests a read-only check, which the agent can infer as an alternative to set_license_key. There is no explicit statement of when to call this versus quick_check, get_version, or set_license_key, and no prerequisites or exclusions are given.

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