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

With no annotations provided, the description carries the full behavioral burden and fully delivers: it discloses that this is the only mutating tool, that dry runs execute on a temporary copy of the repo surface, that the output lists files that would be created, overwritten, or deleted, and that real writes are destructive and update the kit stamp. The risk profile is surfaced, not hidden.

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 long but appropriately so for a high-risk mutation tool with 7 parameters; the critical write-vs-read-only distinction is front-loaded and the Args/Returns structure aids scanning. Minor redundancy: dry_run default semantics are fully explained in the third paragraph and then restated in the Args block.

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 complex mutating tool with 7 optional parameters, no annotations, and only a string output schema, the description covers everything needed to call it correctly: purpose, side effects, the safety gate, all parameter semantics, and the Markdown return format. An agent could invoke it safely and correctly with no additional information.

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%, and the description fully compensates: all 7 parameters receive value domains (clients list, preset categories, language choices, codegen options), default sources (server start value, profile setting, or fixed default), and behavioral meaning (with_overlay copies, keep_unselected_clients prevents deletion). Nothing is left to inference.

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 opening sentence states a specific verb and resource: install kit files (hooks, agents, commands, mcp.json, stamp) into the app repo. It also explicitly differentiates from all siblings by declaring this is the only MCP tool that writes to disk while the rest of the server is read-only, making selection unambiguous without opening any 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?

Names the manual alternative (cloning the kit and running scripts/bootstrap-project.sh) and explains why this tool supersedes it. It also prescribes the safe workflow: dry_run=True is the default planning mode, actual writes require explicit dry_run=False, and it warns that PreToolUse hooks catch Bash/Edit/Write rather than MCP tool names — clear, actionable guidance on when and how to invoke.

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. It discloses the mechanism (git rev-parse/diff --name-only), the fact that it does not read module contents, and that it only concerns static snapshot files. It also lists the return cases: current/changed (+list of files), no stamp, no local git history. This is thorough behavioral disclosure, including limitations and edge cases.

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?

Although the description is somewhat long, every sentence serves a purpose: it states the core check, the cheap method, the scope exclusion (modules), and the return format. It is front-loaded with the main purpose and then details. No redundancy or 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?

The tool has no parameters, an output schema exists, and the description covers the behavior, the return format (Markdown with status), and edge cases (no stamp, no history). It is complete for an agent to understand what it does and what to expect. The description also clarifies the distinction from sibling tools, so nothing 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 has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the schema coverage is 100% (vacuously). No additional parameter semantics are 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's purpose: 'Sprawdź czy kit zmienił się od ostatniego bootstrap-project.sh' (Check if the kit changed since the last bootstrap-project.sh). It specifies the resource (kit) and the action (check status), and distinguishes itself from siblings by explicitly noting that modules are handled live by get_bundle/get_overlay, so this tool only concerns files that bootstrap copies. This is a specific verb+resource with clear 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?

The description explains the context of use: it's a cheap check comparing a stored commit to HEAD, and it clarifies that module files are not covered because they are read live elsewhere. This implies when to use this tool (to decide if re-bootstrap is needed) and when not to (for modules). It doesn't explicitly name alternatives but does reference get_bundle/get_overlay, providing enough 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?

With no annotations, the description carries the behavioral burden and does disclose the key behavior: it concatenates all module Markdown and appends an overlay if present. It also signals a read operation via 'Pobierz'. It does not discuss failure modes or permissions, but for a simple fetch tool that is a minor gap.

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 compact, front-loads the core purpose, and uses a clear Args/Returns structure. Every sentence adds information with no filler.

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 single-required-parameter read tool with an output schema, the description covers purpose, parameter meaning, and return format. It omits exact allowed bundle names and error behavior, but these are not critical for a straightforward fetch by name.

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 only labels the property 'Name', so the description compensates by defining name as the bundle identifier and giving concrete examples ('backend', 'frontend', 'architecture', 'full'). It could be stronger with an exhaustive enum or validation rules, but the compensation is sufficient for correct invocation.

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 ('Pobierz' – fetch) and a precise resource ('pełną treść bundle'a instrukcji'), and clarifies that the result is the combined Markdown of all modules plus optional overlay. This distinguishes it from siblings like get_module (single module) and list_bundles (listing bundles).

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 this tool is for retrieving the full assembled content of a bundle and gives name examples, but it does not explicitly state when to prefer it over get_module or get_overlay, nor does it mention exclusions. Usage context is left largely to inference.

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 provided, the description carries the full burden. It discloses the return type (Markdown string with flag value and client IDs) and explicitly states it does not modify bundle content, implying a read-only operation. It does not cover edge cases like errors or auth, but for a simple getter this is adequate and adds meaningful behavior context.

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: one sentence states the purpose, a second clarifies scope, and a return line specifies output. Every sentence earns its place, and the primary purpose is front-loaded. No fluff or redundancy.

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 tool with an output schema (the return type is described), the description is fully adequate. It tells the agent what the tool does, what it returns, and that it is side-effect-free. Nothing essential is missing for correct invocation.

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 has zero parameters, so the schema already covers everything trivially. The description adds no parameter details, but that is not a gap since there are none. The baseline of 4 applies because the description could have mentioned that no parameters are needed, but it is not necessary given 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 states a clear, specific purpose: listing AI clients configured at MCP startup, with the flag and environment variable named. It also clarifies it deals with template installation metadata and explicitly says it does not alter bundle content, distinguishing it from content-related tools. The verb 'Lista' (list) and resource 'klientów AI' make the action unmistakable.

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 context by noting it covers metadata and does not change bundle content, which hints at when to use it (for client configuration info). However, it does not explicitly mention when not to use it or name alternative tools, and no comparison to siblings is provided. The guidance is implied rather than explicit.

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 must disclose behavior. It only states the return value and its possible values, but does not mention whether the operation is read-only, if it can error, or any prerequisites. It does not explicitly state it is a safe getter, leaving behavioral aspects undisclosed.

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 concise, front-loaded with the purpose, and uses a structured 'Returns' block to enumerate possible values. It contains no fluff and is appropriately sized for a simple getter.

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 has no parameters and an output schema is present. The description explains the semantic meaning of each return value, which is valuable context beyond the schema. It could mention default behavior or error handling, but for a simple getter, it is reasonably complete.

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, and schema coverage is 100% (since there are no parameters to document). The description adds value by explaining the meaning of the return values, which is beyond schema requirements. Baseline for no parameters is 4, and the description meets that.

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 returns the current API client generator selection ('Aktualny wybór generatora klienta API') and lists the possible return values (orval, none, graphql) with their meanings. It distinguishes itself from sibling getters by focusing on this specific configuration.

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 the tool is used to check the current codegen setting but does not explicitly state when to use it vs. alternatives. It lacks exclusions or context about typical invocation (e.g., before generating clients). The purpose is clear enough for basic use, but no explicit usage guidance is provided.

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 present, so the description must carry the behavioral disclosure burden. It does disclose that the return value is a Markdown string, but it says nothing about side effects, read-only behavior, prerequisite profile state, or failure behavior.

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 two short lines with no filler. The main purpose is front-loaded and the return type is stated directly, which is ideal for a tool of this simplicity.

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 this is a zero-parameter getter with an output schema, the description covers the essential scope and return format. It would benefit from explicit usage guidance or a read-only statement, but the low complexity makes it sufficiently complete.

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 has zero parameters, and the no-parameter baseline is 4. The description appropriately avoids inventing parameter details and focuses on what the tool returns.

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 resource ('enabled modules and bundles') and a clear scope ('current profile'), so an agent understands what the tool returns. It does not explicitly contrast itself with siblings like list_modules or list_bundles, but the 'enabled ... for current profile' phrasing narrows the purpose enough to avoid major ambiguity.

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 use this tool versus alternatives such as list_modules, list_bundles, get_bundle, or get_overlay. 'For current profile' implies a profile-specific use case, but no conditions, exclusions, or alternative recommendations are provided.

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 must carry the burden. It discloses the return type and content, and the 'get' verb implies a read-only operation, but it does not explicitly state whether the tool has side effects, requires context, or depends on any session state. For a zero-parameter getter this is minimally acceptable 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?

The description is compact: one purpose sentence followed by a structured 'Returns:' line with the type and content. Every piece contributes useful information, and the purpose is front-loaded before the return detail.

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 and an existing output schema, the description covers what an agent needs to know to invoke the tool and interpret the result. It could be slightly more explicit about the intended use case or what 'title vs prose policy' means, but for a simple getter it is largely complete.

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 has zero parameters, so there are no parameter semantics to document. Schema description coverage is effectively complete with an empty properties object, matching the baseline for no-parameter tools.

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 resource ('get_language' means current instruction language) and specifies what is returned: Markdown with the language code, the `core:language-*` module, and EN/PL rules. It is specific enough to distinguish the tool from siblings like get_overlay or get_codegen, though the phrase 'tytułów vs prozy' remains somewhat 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?

The description gives no guidance on when to call this tool versus alternatives such as get_overlay or get_codegen. It does not state contexts, exclusions, or relationships to sibling tools, so an agent must infer usage from the name alone.

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 add useful behavioral context by stating the return format (Markdown string) and that the ID comes from a manifest with an example. However, it does not disclose failure behavior, side effects, or availability constraints, though these are relatively minor for a simple read-style getter.

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 compact and well-structured: a one-sentence purpose, then Args and Returns sections. There is no filler, and each line adds necessary information for invoking the tool correctly.

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 tool with one required parameter and a string return, the description is largely complete: it names the resource, explains the parameter, and specifies the output format. Missing usage context and failure semantics are gaps, but they do not prevent a correct call in the common case.

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 schema provides only a type and title, with 0% description coverage. The description compensates fully by explaining that module_id is an ID from the manifest and giving a concrete example (stack:django-drf:backend-standard). This makes the parameter meaning and expected format clear.

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 a specific verb ('Pobierz' / fetch) and resource ('pojedynczy moduł instrukcji') by identifier, so an agent can understand the core action. It does not explicitly distinguish this tool from siblings such as get_index or get_bundle, but the 'module' resource is distinct enough to make the purpose unambiguous.

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 about when to use get_module versus alternatives like list_modules, get_bundle, or get_overlay. The description only explains the mechanism (fetch by module_id), not the selection context or any 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?

No annotations are provided, so the description carries the burden. It discloses that the tool returns the content of `.ai/project.md` and other overlays indicated in the profile, which is useful behavioral context. However, it does not mention whether the tool can fail (e.g., missing overlay), whether it reads from the local filesystem, or any side effects. It is a read operation by nature, but that is not explicitly stated.

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 short and front-loaded with the main purpose in the first sentence. The Returns section adds useful detail about the specific files involved. It is efficient, though the Polish language may be slightly less universally accessible than English for an AI agent, and the Returns block could be considered redundant with 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?

Given the tool has no parameters and an output schema exists, the description is mostly complete for a simple fetch operation. However, it lacks context about failure modes (e.g., what happens if `.ai/project.md` does not exist), whether the overlay is loaded from the current workspace, and how the returned string is formatted. These gaps are minor for a zero-parameter read tool but still leave some ambiguity.

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 has zero parameters, so the schema provides no parameter semantics to rely on. The description compensates by explaining what the tool returns and where the content comes from (`.ai/project.md` and profile-indicated overlays). With 0 params, a baseline of 4 is appropriate because the description clarifies the tool's input-free nature and its output source.

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 ('Pobierz' = download/fetch) and resource ('overlay projektu' = project overlay), and clarifies it contains unique instructions for this repo. It distinguishes itself from siblings by specifying it retrieves `.ai/project.md` and other overlays indicated in the profile, which is a clear purpose even though it doesn't explicitly name a sibling.

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 when to use it: when you need the project-specific overlay instructions. It does not explicitly state when not to use it or name alternatives among siblings like get_language or get_codegen. The context is clear enough for an agent to infer usage, but there is no explicit routing 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?

No annotations are provided, so the description carries the behavioral burden. It discloses that the return value is a Markdown string listing bundles and module counts, which adds useful information. It does not discuss side effects or errors, but 'list' implies a read-only operation and the tool has no parameters.

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 two short, purposeful lines: an action sentence followed by a return-value line. There is no filler or redundancy.

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 parameterless list tool with an output schema, this description is complete: it names the resource, the scope, and the return format. Nothing essential is missing for an agent to invoke it 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?

The input schema is empty with zero parameters, so the baseline is 4. There are no parameter semantics to explain, and the description still adds the useful implicit context of 'current project profile'.

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 ('Lista' / list), a clear resource ('bundle'i instrukcji'), and a scope ('dla bieżącego profilu projektu'). It distinguishes itself from siblings like get_bundle (which implies retrieving one specific bundle) and list_modules (which targets a different resource).

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 when to use it: when you need the list of bundles for the current project profile. However, it does not explicitly mention alternatives or when not to use it, leaving sibling differentiation to inference.

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. It discloses the return type (Markdown string with identifiers and titles) but does not state read-only nature, side effects, auth requirements, or any failure behavior. Minimal behavioral detail for a tool with no annotation coverage.

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 with no fluff. The purpose is front-loaded, and the return type is stated clearly. Perfectly sized for a simple list tool.

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 0-parameter list tool with an output schema present, the description covers what it returns. It doesn't explain the concept of 'instruction-kit' or the manifest, but that context may be understood from the tool family. Slightly lacking in contextual depth but adequate.

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 has zero parameters, so the description need not explain parameter meanings. The schema covers 100% with no parameters, and the description adds nothing about parameters, but per rubric 0 params baseline is 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?

The description states a specific verb ('Lista wszystkich modułów') and resource ('instruction-kit manifest'), clearly indicating it retrieves all modules. It distinguishes from siblings like get_module by specifying 'all modules', though it doesn't explicitly name alternatives.

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 guidance on when to use this tool versus alternatives like get_module, list_presets, or list_bundles. There are no prerequisites or conditions provided.

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?

There are no annotations to carry the behavioral burden, so the description must disclose traits itself. It partially does so by stating the return format (Markdown with categories such as '_base', 'shop'), and listing is naturally read-only. However, it does not mention whether it scans nested directories, errors on missing profiles, or reflects current workspace state.

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 two purpose-built lines: one stating scope and source, one stating return type and content. It is front-loaded with the main action and contains no filler.

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 parameterless listing tool this is nearly complete: it names the resource, the source path, and the returned Markdown format. It lacks explicit mention of failure behavior or environment context, but the scope is simple enough that the gap is minor.

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 has zero parameters and no required parameters, so there is nothing for the description to clarify about arguments. The 100% schema coverage on an empty properties object supports assigning the baseline of 4 for no-parameter tools.

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 action ('Lista dostępnych presetów' = list available presets), identifies the exact resource location ('profiles/*.yaml' in instruction-kit), and differentiates from sibling listing tools like list_modules and list_bundles by naming the preset domain. There is no ambiguity about what the tool does or returns.

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 purpose implicitly tells an agent to use this tool when it needs available presets in profiles/*.yaml, but the description gives no explicit guidance about when not to use it or how it compares to sibling list tools. With zero parameters and a narrow scope this is minimally adequate but leaves routing to inference.

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