Chris Pereira (彭家荣): China business expert

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

readOnlyHint=true already tells the agent this is a safe read with no side effects, so the description's burden is lower. Its contribution is the content inventory, which stands in for the missing output schema by telling the agent roughly what data comes back; it adds nothing on freshness, size, or formatting.

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 fragment with zero filler; every item in the list maps to a distinct part of the payload. It would be marginally stronger with a leading verb, but nothing is wasted.

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

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

With no input parameters and no output schema, the description's key job is to tell the agent what data it will receive, and the content inventory does that thoroughly. Nothing needed to call this zero-arg, read-only tool correctly is missing.

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

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

The tool takes zero parameters, so there is no parameter semantics to explain — baseline 4 applies. The description correctly spends no words on arguments and puts them all into describing the returned payload instead.

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?

Enumerates precisely what the profile resource contains (bios, titles, books, topics, languages, speaking history, photos, contact routes), which clearly delimits it from siblings like search_quotes and search_coverage. It never states a verb ('returns'/'fetches'), relying on the name and title to carry the action, so it falls short of a clean verb+resource phrasing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the place to get biographical/profile data, but nothing says when to prefer it over search_coverage or search_quotes, nor whether it is a prerequisite for send_inquiry. No exclusions or alternatives are named.

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 readOnlyHint=true already declaring the safety profile, the description adds useful context beyond annotations: the corpus size (225+), the returned fields, and the empty-query fallback behavior. It stops short of covering pagination semantics or how matches are ranked.

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 packs corpus scope, return fields, and the empty-query rule with no filler. Every clause carries information an agent would otherwise have to guess.

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 compensates by listing the fields returned (outlet, title, date, link, quotes, summary). What is missing is any hint about result ordering or total-count behavior for a 225+ corpus, but overall it is sufficient to call correctly.

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

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

Schema description coverage is 100%, so both parameters are already documented, including the empty-query behavior and the outlet/topic examples. The description adds no syntax or format detail beyond what the schema states, so the 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 names a specific verb and resource and enumerates the corpus (interviews, quotes, TV appearances, op-eds) plus the returned fields, so the agent knows exactly what is searched. It does not explicitly differentiate itself from the sibling search_quotes, which overlaps thematically, so it falls short of a 5.

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 line 'Empty query returns the most recent' gives a concrete browse-mode use case, which is genuine usage guidance. However, there is no statement of when to prefer this over search_quotes or get_profile, and no exclusions or 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?

readOnlyHint=true already covers the safety profile, yet the description still adds value by enumerating what each result contains (text, date, outlet, source_url, ready-made attribution) — important since there is no output schema. It stops short of stating result ordering for non-empty queries or whether matching is fuzzy or exact.

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 tight sentences, front-loaded with the purpose and followed by result shape. The example list is slightly redundant with the schema's query description, but the cost is small.

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 usefully compensates by listing returned fields and the attribution convenience. For a two-optional-parameter read tool with annotations covering safety, nothing critical is missing beyond result ordering and match behavior.

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

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

Schema coverage is 100% and both parameters are documented there, so the baseline is 3. The description's query examples are richer than the schema's, but its "empty query returns the latest" clause largely restates what the query parameter description already says, and it adds nothing about limit.

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 ("search his curated quotes") and seeds it with concrete topic examples ("trust", "Shenzhen", "tariffs"), which tells an agent exactly what corpus is being queried. It does not explicitly distinguish itself from the similarly named sibling search_coverage, so the agent must infer the split from names alone.

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 line "Empty query returns the latest" gives one concrete usage condition (browse mode vs topic mode). However, there is no guidance on when to use this rather than search_coverage or get_profile, and no exclusions or prerequisites are stated.

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=false, openWorldHint=true and destructiveHint=false, so the agent knows this is a non-destructive outbound action. The description adds genuinely useful context beyond that: the message is delivered by email, replies go to the supplied address, and turnaround is typically 24 hours — an expectation-setting detail not in any structured field. It does not mention that a sent email cannot be recalled or any rate limits, which keeps it below 5.

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

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

Two sentences, front-loaded with the action and recipient, with the request categories and response expectation packed in without filler. Nothing is redundant.

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 15-parameter submission tool with full schema coverage and no output schema, the description covers the action, the audience, and the response loop. It leaves conditional parameter grouping (which fields matter for 'speaking') entirely to the schema, which is acceptable given 100% coverage.

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 every one of the 15 parameters carries its own description, including the 'speaking:' prefixes that scope conditional fields. The description's only added meaning is restating the type categories and clarifying that the reply goes to the given address, which the schema already says. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Send a request straight to Chris Pereira by email') and immediately enumerates the request categories accepted: media comment/interview, analyst briefing, speaking invitation. This is unambiguously distinct from the read-only siblings (get_profile, search_coverage, search_quotes).

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 enumerated request types ('media comment or interview, analyst briefing, or an invitation to speak (keynote, panel, podcast, show guest, training)') tell an agent when this tool applies. It stops short of explicit exclusions or naming alternatives, though the siblings are obviously different in kind (lookups vs. outreach).

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