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

No annotations exist, so the description carries the full disclosure burden. It does reveal a genuinely non-obvious trait — statefulness ('guarda contexto (chat_id)') — which affects call sequencing (reuse the ID to continue). But it stays silent on the external Perplexity service, cost/latency implications, and return behavior, which matter for an unannotated conversational 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 sentences and roughly 25 words: purpose and statefulness are front-loaded, the usage rule follows, and there is zero filler. Every sentence carries a distinct piece of information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema already covers all 4 parameters well, so the description doesn't need to restate them. But with no output schema and no annotations, the description omits what the agent will receive back and why this exists alongside deep_research; 'Pepe' is invoked without explaining the persona. Adequate for a basic call, short of full guidance.

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 `message` parameter is already documented in detail (CPQO fields, follow-up rule). The description's short-turn advice mostly restates the schema's follow-up note ('puede acotarse si CONTEXT ya está en el historial'), so it adds only marginal meaning beyond the input schema. 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?

The description opens with 'Hilo conversacional con Pepe' — a specific resource (a named conversational entity) plus the key trait 'guarda contexto (chat_id)' — making the purpose unmistakable next to the search/retrieval siblings. It doesn't explicitly name or exclude any sibling like deep_research, though the chat-vs-search boundary is evident.

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 concrete message-format rule ('Usa CPQO en `message` o turnos cortos si el hilo ya cargó el brief') that helps an agent invoke correctly. But it offers no guidance on when to pick this tool over alternatives — notably deep_research, a sibling that could plausibly overlap with a research-focused chat persona.

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 of behavioral disclosure. It only says the tool contrasts code/patterns with current web state; it does not explain how results are presented, whether sources are returned, what 'certeza' means operationally, or any limitations. This is thin but not misleading.

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: two short sentences with the main action front-loaded. It avoids irrelevant details, though the second sentence partially repeats what the parameter schema already documents.

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-parameter tool with a well-documented schema, the description is sufficient for basic invocation. However, it lacks output expectations and sibling-tool routing, and it does not clarify what kind of response the agent should expect (e.g., structured findings, links, confidence levels).

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 for the single parameter is 100%, with a detailed description and example already present. The tool description reinforces the CPQO format and mentions including stack/snippet/pattern and the type of certainty needed, which is helpful but adds little 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 uses a specific verb ('contrastar') and resource ('código o patrones con estado actual en la web'), making clear this tool checks code/patterns against current web state for deprecation-related facts. It does not explicitly distinguish from siblings like get_documentation or search, but the deprecation/replacement/migration focus is enough to identify its purpose.

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 the tool: when you need to check for replacements, deprecation dates, or migration guidance. However, it provides no explicit guidance on when not to use it or which sibling tools are better suited for general web searches or documentation lookups.

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 must carry behavioral disclosure. It mentions more passes/sources than search, but does not describe output format, latency, cost, side effects, or potential warnings. It focuses on input requirements rather than what happens when the tool runs.

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 dense sentences with no filler. It front-loads the core differentiator (`más pasadas/fuentes que search`), then gives actionable input guidance and the skill reference.

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 tool, the description covers what it does, when to use it, and the required query structure. However, with no output schema and no annotations, the absence of any statement about the return format or expected deliverable leaves a meaningful gap for an agent.

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 baseline is 3. The description adds useful context about the CPQO format and the need for multiple OBJECTIVES, reinforcing the schema's query guidance, but it does not materially extend the schema definitions.

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 identifies the tool as a broad research mode with more passes/sources than `search`, giving a clear functional identity. It lacks a direct verb like 'runs' or 'performs', but the comparison with `search` makes the purpose specific enough to distinguish it.

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 explicitly positions the tool relative to `search` ('más pasadas/fuentes que `search`') and gives practical guidance about needing many OBJECTIVES for large topics. It does not state explicit exclusions or when to prefer alternatives like `chat_perplexity`, but the context is 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 some behavioral burden. It does disclose a key behavioral trait: it returns clean text with less noise than the original page. However, it does not mention network effects, failure modes, accessibility limitations, or what happens when following internal links, leaving notable 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?

The description is short and front-loaded, stating the main action before the usage boundary. Every sentence earns its place, though the cryptic 'CPQO' reference costs some clarity.

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 tool with a simple input schema and no output schema, the description gives enough orientation to attempt a call. However, it leaves return format and failure behavior to inference, and the boundary with search siblings is only partially explained.

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 URL and depth parameters are already documented in the schema. The description adds no additional parameter meaning beyond that, which is acceptable given the baseline for high schema coverage.

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 and resource: extracting clean text from a URL. It also differentiates the tool from search by framing it as a way to bring specific evidence. The unexplained acronym 'CPQO' slightly muddies the distinction, but the core purpose is clear.

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 explicitly says when to use it ('sirve para traer evidencia puntual') and when not to ('No reemplaza CPQO en search'). It does not name alternative sibling tools directly, but it clearly delimits this tool as targeted evidence-gathering rather than general search.

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 of behavioral disclosure. It states that the operation happens 'vía Pepe' and describes the query format, but it does not explain what the tool actually returns, whether it is read-only, what dependencies exist, or what failure modes might occur. This is a significant gap for a no-annotation 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?

The description is a single efficient sentence that front-loads the core purpose and then gives the key input requirement. No fluff, no repetition of schema details. Every word earns its place.

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 one-param tool with no output schema, the description adequately covers the input format and intent. However, it omits what the agent can expect as a result (e.g., a list of APIs, a comparison table, a research brief) and doesn't clarify what 'vía Pepe' means in practice. It's workable but leaves behavioral gaps.

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 is 3. The description adds meaning by specifying what kinds of constraints to include in the query (región, SLA, presupuesto) and emphasizes comparison questions and measurable objectives, which goes beyond the schema's format-only description. This helps an agent construct a more effective query.

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 specific verbs ('Descubrir/comparar') and a clear resource ('APIs externas'), which distinguishes it from generic search or documentation tools. It doesn't explicitly name sibling tools, but the niche of discovering/comparing external APIs is specific enough. 'Vía Pepe' adds a methodological nuance but isn't fully defined.

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 intended use case—finding or comparing external APIs—is implied clearly, but no explicit when-to-use/when-not-to-use guidance or alternatives are provided. Given siblings like 'search', 'deep_research', and 'get_documentation', an agent could benefit from clearer routing criteria. The CPQO format is described, but not when to pick this over similar tools.

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, so the description carries the full burden. It mentions 'via Pepe' and deliverables but does not disclose what Pepe is, how results are returned, whether any side effects exist, or any limitations. The behavioral information is minimal and vague.

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 redundancy. The main action is front-loaded, and the query-format guidance is placed immediately after. It is efficient and every sentence contributes.

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 one-parameter tool is simple, and the description effectively covers the required query structure. However, with no output schema and overlapping sibling tools, it lacks clarity on return format, output shape, and decision boundaries between this and similar tools.

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% with a detailed parameter description and example. The tool description adds a concise mapping (stack, failure, deliverables) but mostly repeats what the schema already communicates, so the marginal value is limited.

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 searches official documentation and examples via Pepe, with a specific verb and resource. It distinguishes itself from siblings by emphasizing a structured CPQO query format and deliverables like snippets and breaking changes, though it doesn't explicitly name sibling 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?

The description implies when to use the tool (need official docs/examples) and provides detailed how-to guidance on formatting the query in CPQO. However, it does not explicitly state when to prefer this over siblings like search, deep_research, or chat_perplexity, nor 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?

With no annotations, the description carries the burden of behavioral disclosure. It clearly indicates the tool performs a read-only listing operation and adds context about account-specific Pro models. It does not describe the output format, but for a simple listing tool with no parameters, this is adequate.

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, front-loaded sentence that conveys the action, scope, and usage context with no wasted words. It is highly efficient and easy to parse.

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, no output schema, and a simple list operation, the description is nearly complete. It could explicitly state that the returned model names are valid values for the `model` parameter, but the implication is clear from the usage hint. The tool is simple enough that this short description suffices.

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 has zero parameters, so the baseline is 4. There are no parameter descriptions to provide, and the description adds value by explaining the purpose and usage context rather than repeating schema information.

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 (list) and a specific resource (Pro models available in your Perplexity account). It also differentiates from sibling tools by positioning itself as the preparatory step before setting the `model` parameter in search/chat.

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 phrase 'antes de fijar model en search/chat' gives clear temporal context for when to use this tool and implies it should be used before search/chat operations. However, it does not explicitly state when not to use it or name alternative tools beyond the search/chat reference.

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 of behavioral disclosure. It reveals that this is a one-pass research tool (not exhaustive), and it quantifies how `detail_level` affects output depth. It does not mention rate limits or authentication, but for a non-destructive search tool the core behavioral trait is well disclosed.

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 three concise sentences: it front-loads the purpose, explains the key parameter, and presents the alternative tool. Every sentence contributes actionable 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 simple search tool with fully documented parameters, the description is largely complete: it covers purpose, scoping, parameter semantics, and sibling routing. The only notable omission is the relationship with `chat_perplexity`, which could clarify when a conversational interface is preferred, but this is minor given the schema covers the remaining details.

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 is 3, but the description adds meaningful value by mapping `detail_level` values to OBJECTIVES counts and referencing the pepe-research-brief skill. This goes beyond the schema's simple enum descriptions and helps the agent choose a parameter value correctly.

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 performs single-pass web research via Perplexity, giving a specific verb and resource. It also explicitly distinguishes itself from the sibling `deep_research` by describing the latter as the alternative for extensive multi-source reports.

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 provides concrete guidance on choosing `detail_level` based on desired OBJECTIVES count (brief ≈1–2, normal ≈3–5, detailed ≈6–8). It also explicitly instructs the agent to use `deep_research` when a broader multi-source report is needed, making the selection criteria clear.

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