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

With no annotations, the description carries full burden but only states that it adds a prompt and lists required fields. It does not disclose side effects, permissions needed, validation behavior, or what happens on duplicate entries, leaving key behavioral traits unaddressed.

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 sentences, front-loading the core action. The second sentence redundantly lists parameters already in the schema, slightly reducing efficiency, but overall it is appropriately sized.

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 should explain the creation outcome (e.g., success response, ID return) and any behavioral context. It fails to do so, leaving the agent without essential post-invocation expectations.

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 fully documents all parameters. The description repeats the required and optional parameter names, adding no meaning beyond what the schema provides; a 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 states a specific verb ('Adiciona') and resource ('novo prompt de AI à coleção'), making the tool's purpose clear. It implies creation as opposed to update, but does not explicitly name or differentiate from sibling tools like update_prompt or delete_prompt.

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 use this tool versus alternatives, nor does it mention prerequisites or context. It only lists required fields, which is not usage 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 full burden. It says nothing about whether this is a persistent mutation, whether authentication is required for cloud providers, what happens to existing data, or whether migration is destructive. The 'migrate' parameter implies data movement but the description never explains it. For a configuration-mutating tool with zero annotation coverage, this is severely underspecified.

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 short sentences with no filler, and the core purpose is front-loaded. Efficient, though extremely minimal.

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?

A mutation tool with no annotations, no output schema, and a migration capability that is never explained. The description does not address permissions, persistence, or data-handling implications, leaving significant gaps for an agent deciding whether to invoke 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 schema already documents all three parameters including the enum values and the migrate default. The description adds no syntax, format, or behavioral detail beyond what the schema provides. 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?

States a verb and resource ('Configura o storage provider e caminho') but is vague about what configuration actually means and what effects it has. It does not differentiate from camera-ready siblings like get_storage_config or list_storage_providers, though it does gesture at provider switching.

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 get_storage_config (reading config) or list_storage_providers. The mention of switching providers implies a use case but does not state prerequisites or consequences.

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 exist, so the description carries the full behavioral burden. It implies a destructive mutation but says nothing about permanence, reversibility, required permissions, or side effects on related data — all critical for a delete tool.

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 zero filler. For a one-parameter tool, this is appropriately sized and wastes no tokens.

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 is structurally simple (one param, no output schema) and the schema handles the input, but a destructive operation with no annotations leaves the agent without essential context about irreversibility or confirmation requirements.

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?

Only one parameter, and schema coverage is 100%, so the schema already documents 'id' as 'ID do prompt a ser removido'. The description's 'pelo ID' adds no meaning beyond that, 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 ('Remove um prompt') plus the scoping key ('pelo ID'), so the operation is unambiguous. It does not explicitly contrast itself with siblings like update_prompt, but 'remove' is distinct enough that differentiation is not strictly needed.

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 when-to-use, when-not-to-use, or prerequisite information is provided. It doesn't say whether the removal is permanent, whether confirmation is needed, or what to do instead if the prompt should merely be modified.

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 must carry full behavioral disclosure. It does not indicate whether this is a read-only operation (though implied by 'Lista'), nor does it describe whether results are cached, ordered, or how many categories might be returned. It also doesn't state whether the list is exhaustive or affected by other filters.

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 a single, efficient sentence that front-loads the action and resource with no unnecessary words. It is appropriately sized for a parameterless list operation.

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 simplicity of the tool (no parameters, no output schema, no annotations), the description is minimally adequate. However, it lacks any behavioral context that might help an agent understand the nature of the returned list (e.g., is it a distinct set across all prompts, does it include empty results, etc.), leaving some ambiguity for a read operation.

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 accepts zero parameters, and the description appropriately does not discuss parameters. The baseline for zero parameters is 4, as there are no semantics to convey beyond what is already clear from 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 specific verb ('Lista') and resource ('categorias únicas dos prompts salvos'), clearly defining the scope as unique categories derived from saved prompts. It doesn't explicitly distinguish itself from the sibling get_tags, which is a similar extraction tool, but the specificity of 'categories' versus 'tags' provides implicit 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 implies the use case (obtaining category list) but offers no explicit guidance on when to use this tool versus alternatives such as get_tags or list_prompts. There is no mention of prerequisites or contexts where it should be invoked.

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 full behavioral burden. It does not disclose whether the tool is read-only, whether it affects state, performance implications, or the return format. It only states the type of data returned.

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 with a clear front-loaded purpose. It is appropriately sized for a zero-parameter tool and does not waste words.

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 read-only tool with no output schema, the description is minimally adequate but lacks behavioral details like read-only nature, cache behavior, or how the statistics are computed. It gives the agent enough to know what the tool returns but not enough to confidently call it in all contexts.

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 0 parameters, so parameter semantics baseline is 4. No parameter information is needed or expected in the description.

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 in Portuguese: 'Retorna estatísticas de uso de contexto (tokens estimados por categoria)'. It tells the agent it returns context usage statistics with estimated tokens per category, but does not differentiate from siblings like get_categories or get_prompt_summary.

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?

Implies usage for 'planejamento de context budget' but offers no explicit when-to-use, when-not-to-use, or comparison to alternatives. The sibling get_categories could also return category-related data, so the distinction is left 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?

No annotations are provided, so the description carries the full burden. It says nothing about whether id/name require exact matches, whether id takes precedence when both are supplied, what happens if not found, or the return format. The 'COMPLETO' hint is the only behavioral signal.

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 short sentences, front-loaded with the action and scoping note. Efficient, though the capitalized 'COMPLETO' is slightly noisy styling rather than added structure.

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 2-param lookup with no output schema and no annotations, the description is minimally adequate. It omits the sibling distinction (get_prompt_summary) and selection behavior between id/name, which the 100% schema coverage partly compensates for on parameters but not on routing.

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 schema already documents both parameters as 'use id OU name'. The description references both identifiers but adds no resolution/precedence semantics beyond what the schema states, 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 clear verb+resource: retrieves the COMPLETE content of a prompt by id or name. This is unambiguous and distinguishes itself functionally from get_prompt_summary (which presumably returns partial), though it does not name that sibling explicitly. The 'COMPLETO' emphasis implies contrast but leaves it to inference.

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?

Says 'Use apenas quando precisar do conteúdo inteiro' (use only when you need the full content), which implies a when-to-use condition favoring get_prompt_summary otherwise. However it does not name the alternative tool or explain the tradeoff, so 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 carries the burden. It discloses the key behavioral trait — that only the summary/description is returned, not the full prompt — which is the essential fact for an agent. However, it says nothing about truncation, permissions, or exact return shape, leaving moderate gaps 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 short sentences: the first states what the tool returns and why it is efficient, the second routes to the alternative. No filler, and the core purpose is front-loaded.

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 single-parameter read tool, the description covers purpose, return scope, and the sibling alternative. With no output schema, it could say slightly more about the summary contents, but nothing critical 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?

Schema description coverage is 100% with a single required 'id' parameter whose type and meaning are already documented in the schema. The description adds no syntax, format, or constraint details beyond what the schema provides, so the baseline of 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?

States a specific verb and resource (obtains the summary/description of a prompt) and explicitly contrasts itself with the sibling get_prompt for full content. An agent can distinguish the two without opening either 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 alternative tool (get_prompt) and the condition that selects it ('eficiente para contexto'), giving clear routing guidance. It doesn't state an explicit when-not-to-use case beyond the implicit 'if you need full content', which is why it falls just short of 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 provided, so the description carries the full burden. It discloses the payload contents (provider, path, last sync), which is genuinely useful, but says nothing about whether the call is safe/read-only, whether auth or elevated permissions are required, or whether the 'last synchronization' field may be null when never synced.

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 the resource first and the return fields in parentheses. Every clause earns its place; nothing is repeated from the schema.

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 input parameters and no output schema, the description is the only place return values can be described, and it does list them. It is complete enough to call correctly, though it omits any note on freshness, caching, or error behavior when storage is unconfigured.

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 per the rubric the baseline is 4. There is nothing for the description to clarify beyond the empty schema, and it does not waste words inventing parameters.

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 ('Retorna a configuração atual do storage') and enumerates the returned fields (active provider, path, last sync). It is clearly distinguishable from configure_storage by the read-only framing, though it never names its 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?

Usage is only implied: 'configuração atual' signals a read of current state as opposed to configure_storage's mutation. There is no explicit when-to-use, no mention of list_storage_providers as the alternative for enumerating providers, and no prerequisites.

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 behavioral burden, but this is a trivial zero-parameter read operation where 'Lista' adequately signals the read-only nature. It does not state whether tags are scoped globally or per user/workspace, nor the return shape, leaving modest gaps.

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 that fully conveys the operation with no filler. It is appropriately sized for a parameterless listing 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 zero-param list tool with no output schema, the description is adequate but does not say what the returned tags look like, how many, or whether they are deduplicated across all storage providers. It also does not address the sibling get_categories boundary.

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 no parameters, which is the baseline-4 case: there is nothing for the description to clarify beyond what the empty schema already communicates.

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 ('Lista') and resource ('tags únicas usadas nos prompts'), so the agent knows it enumerates distinct tag values. It does not explicitly differentiate itself from the sibling get_categories, which is the one closely related tool an agent might confuse it with.

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 statement of when to use this tool versus get_categories, list_prompts, or the other listing tools, and no prerequisites or exclusions. Usage must be inferred 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 must carry full behavioral burden. It mentions that by default it returns only metadata for context efficiency, and that the 'compact' parameter can change this, but it does not disclose side effects, rate limits, or authentication requirements. Since there are no annotations, a 3 reflects that it gives some behavioral context but is not comprehensive.

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 a single sentence that is front-loaded with the core action, followed by important caveats about metadata and an explicit pointer to get_prompt. No wasted words.

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 there is no output schema and the tool is a simple list operation with full schema coverage, the description provides enough context: it explains the default metadata-only return and points to get_prompt for full content. It could mention pagination or ordering, but those are not critical 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?

Schema coverage is 100%, so the schema already documents all parameters thoroughly. The description does not add meaning beyond the schema, as it only repeats that filters are supported. Baseline 3 applies when the schema does the heavy lifting and the description does not compensate further.

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?

Clearly states what the tool does: lists saved prompts and supports filtering by category, tags, or search. Distinguishes itself from get_prompt by mentioning that get_prompt retrieves full content. However, it does not explicitly state that it returns only metadata as opposed to full content in the main clause, though it does say 'retorna apenas metadata'. It is mostly clear but lacks explicit differentiation from all siblings like get_categories.

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?

Provides a clear usage pointer: 'Use get_prompt para conteúdo completo', indicating when to use an alternative. However, it does not specify when to use this tool versus other list-like tools such as get_categories or get_tags, though those are for different resources.

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 disclosure burden. It does reveal one return characteristic (which provider is active versus merely available), which signals a read-only inspection operation, but it says nothing about permissions, side effects, or output shape.

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 that is front-loaded with the operation and resource, with the return detail following immediately. Slightly redundant in repeating 'disponíveis', but there is 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?

There is no output schema, so the description partially compensates by stating what is returned (active flag plus available providers). For a zero-parameter read tool this is nearly sufficient, though it stops short of describing the full response structure.

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 nothing for the description to disambiguate — the baseline of 4 applies. No parameter-level information is needed or missing.

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 (Lista) and resource (storage providers) and adds scope detail: it reports which provider is active and which are available. It does not distinguish itself from the closely related siblings get_storage_config and configure_storage, which deal with the same storage domain.

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 statement of when to use this tool versus get_storage_config or configure_storage, which operate on the same storage-provider concept. Usage is only implied by the purpose itself, 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.

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

With no annotations, the description carries the full behavioral burden. "Pode atualizar qualquer campo" implies a partial-update semantic (unspecified fields are left unchanged), which is useful, but there is no information on permissions, whether changes are reversible, or what happens to fields omitted. That is a significant gap for a mutation tool.

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 short sentences with no waste and the action front-loaded. It is terse to the point of under-specification rather than 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?

A six-parameter mutation tool with no annotations and no output schema; the description should compensate with permission requirements, partial-update behavior for omitted fields, and error conditions. It provides only the bare minimum.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (id, name, tags, content, category, description) is already documented in the schema. The description's "can update any field" adds only a marginal hint of partial-update semantics beyond what the schema states.

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 ("Atualiza um prompt existente"), so the agent knows this mutates an existing prompt rather than creating one. It does not differentiate from siblings like add_prompt or delete_prompt beyond the verb, but the purpose is 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?

No guidance on when to use this versus add_prompt (create) or get_prompt, and no mention of prerequisites such as needing an existing id or ownership. Usage context is only implied by the name.

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