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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds genuinely useful behavioral context beyond that — a rate/call-frequency caution and batching advice — but says nothing about latency, session behavior, or result limits. It adds some value over the annotations but not rich disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the purpose and then the operational caveat, with no filler. It is efficient, though the purpose half is just a restatement of the obvious name.

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, and the description does note that it returns answer text, which is the essential return contract. Combined with readOnly/openWorld annotations, the safety and shape are covered. However, for a tool with a sibling family and a session-continuation parameter, it does not fully explain return structure or when continuation via backend_uuid applies.

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 sits at 50%: backend_uuid is documented in the schema, while query is not. The description only restates that query is a string, adding no format, length, or example meaning beyond the schema. With coverage near the midpoint, 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 the mechanics clearly — it takes a query string and returns answer text — which is a specific input/output contract. However, it never differentiates perplexity_ask from its three siblings (perplexity_research, perplexity_reason, perplexity_search); it only cites perplexity_search as an alternative batching target, not as a contrasting purpose. An agent cannot tell from this text why it would choose 'ask' over 'search' or 'reason'.

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 real operational guidance: avoid frequent calls and consolidate multiple sub-questions into one query or one perplexity_search call. That is a useful when-to-batch rule. But it offers no explicit criteria for choosing this tool over the sibling research/reason/search tools, leaving the routing decision 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?

The annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds a behavioral constraint beyond those annotations: avoid frequent calls and merge sub-questions into one query or search. It does not disclose rate limits, authentication needs, or return behavior, but it does add relevant call-efficiency 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 two sentences and contains no obvious padding. It is reasonably front-loaded with the official-alignment and reasoning purpose, followed by the usage constraint, though the first clause is somewhat vague rather than maximally informative.

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 three-parameter tool with 33% schema description coverage, no output schema, and three sibling tools, the description leaves significant gaps. It does not explain when to prefer this reasoning tool over perplexity_ask or perplexity_research, nor does it define the query or strip_thinking parameters. The call-efficiency advice is present but insufficient for the definition to be 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?

Schema description coverage is only 33%, with backend_uuid described in the schema and query and strip_thinking undocumented. The description mentions query only as a container for merged sub-questions and adds no meaning to strip_thinking or the required query format, so it fails to compensate for the sparse 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 identifies the tool as the 'reasoning (default reasoning)' variant aligned with official Perplexity MCP, which gives a basic sense of purpose. However, it does not clearly state what kind of reasoning output the agent should expect or how it differs from siblings perplexity_ask and perplexity_research. The only sibling contrast is an indirect reference to merging sub-questions into perplexity_search.

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 advises avoiding frequent calls and consolidating multiple sub-questions into one query or one perplexity_search call, which is useful operational guidance. Still, it does not explicitly say when to choose perplexity_reason over perplexity_ask or perplexity_research, so an agent must infer its place among siblings.

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?

Annotations only declare readOnlyHint and openWorldHint, so the description's disclosure that this is a slow, heavyweight call with cost/rate implications (避免频繁调用) is genuinely additive. It omits anything about result shape or session behavior beyond what the backend_uuid schema description already carries.

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 compact sentences with the heavy-call warning and the preference for lighter siblings front-loaded; there is no filler and every clause carries an instruction.

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

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

With no output schema, the description should say something about what a research call returns, but it does not, and strip_thinking remains undocumented. The cost/latency framing and sibling routing are present, so it is adequate but incomplete for a 3-parameter tool.

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

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

Schema coverage is only 33%: backend_uuid is documented in the schema, while query and strip_thinking are not. The description partially compensates by advising how to shape the query (merge sub-questions into one call), but says nothing about strip_thinking, leaving one parameter unexplained in both places.

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 the resource and character of the operation (深度研究, 重型调用) and explicitly positions it against its siblings by naming ask/search. It is clear enough that an agent can distinguish it from perplexity_ask and perplexity_search without opening a schema, though the core verb is partly restated from the tool name itself.

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 an explicit use-only-when-necessary rule, names the preferred alternatives (优先 ask/search), warns against frequent invocation, and advises consolidating sub-questions into a single call. This is a complete when/when-not/alternative routing instruction.

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?

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely new behavior: it discloses that the current implementation returns answer text with structured fields 'attached where possible', and warns about call frequency. The rate-limit warning and return-format caveat go beyond what the annotations convey.

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?

It is short and the batching advice is actionable, but the first clause ('align with official Perplexity MCP') is meta-noise that does not help an agent call the tool. That padding dilutes an otherwise compact definition.

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

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

With no output schema the description does helpfully sketch the return shape (answer text + optional structured fields), which compensates somewhat. However, with three sibling tools and no differentiation, and query undocumented in the schema, the definition is only minimally complete for an agent choosing among the perplexity_* family.

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 50%: backend_uuid is well documented in the schema (session continuation via structuredContent.backend_uuid), but query has no schema description. The description only implicitly covers query by advising sub-questions be merged into 'one query', which is mild but useful guidance rather than full parameter semantics.

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 verb/resource (web search) and notes it returns answer text, but it opens with meta-commentary about aligning with the official Perplexity MCP rather than stating scope. It never distinguishes itself from the three siblings (perplexity_ask, perplexity_research, perplexity_reason), which leaves the agent guessing what makes 'search' the right pick.

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 efficiency advice ('avoid frequent calls', batch sub-questions into one query) but no when-to-use guidance relative to the sibling tools that exist. No exclusions or alternatives are named, so the agent has no basis for choosing this over perplexity_ask or perplexity_research.

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