Doply

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful context that channels vary by customer type (Kmong buyers use Kmong chat), but says nothing about the response shape or whether contact info is static.

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 parallel sentences (Korean/English) with the usage trigger front-loaded and the channel list immediately after. The bilingual duplication is justified by the tool's locale parameter; no wasted sentences.

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 read-only lookup with no output schema, the description conveys what the agent will get back (the contact channels themselves) and the per-buyer-type caveat. Nothing critical is missing, though a hint about the return format would close the last gap.

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 is a single optional parameter (language) with 100% schema description coverage and a declared enum, so the schema fully documents it. The description adds nothing about the language parameter, which is fine at baseline 3 given the 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 names the resource (contact channels for reaching a person at Doply) and enumerates the concrete channels: email, Kakao channel, and Kmong chat. It is clearly distinct from siblings like search_faq or get_service_info, though the phrasing is a noun label rather than an explicit verb.

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?

"사람에게 직접 문의해야 할 때" / "How to reach a person" gives a clear trigger condition: use when the user needs human contact. It implies, but does not explicitly state, that self-service questions should go to search_faq instead, so the alternative routing 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?

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description's added value is telling the agent which policy areas the payload covers, but it says nothing about whether the answer is static, whether it can be partial, or how it is structured beyond the topic list.

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 leads with the purpose and then lists the covered conditions; nothing is padded. The only cost is the full Korean/English duplication, which doubles length but serves the bilingual audience.

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 static reference-lookup tool with no output schema and a single optional param, the topic enumeration gives the agent enough to decide whether the answer it needs lives here. Only the missing routing against sibling info tools keeps it from a 5.

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 is one optional parameter (language) with a full enum and a 100%-covered schema description, so the schema carries the meaning. The description never mentions the language option or its default, adding nothing on top of the structured field — 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 resource — the required and recommended conditions for running a closed test with Doply — and enumerates the concrete topics inside it (closed track, South Korea release, minSdk, paid apps, no TWA). That is far more than a restatement of the name, though it never explicitly differentiates itself from get_service_info or search_faq.

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 it should call this when it needs eligibility/precondition facts for a closed test. There is no explicit when-to-use statement, no exclusion, and no reference to the sibling tools (get_contact, get_service_info, search_faq) that could also hold related information.

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 state readOnlyHint, idempotentHint, closed-world, and non-destructive, so safety is fully covered by structured data. The description's added value is the content inventory of what the response contains, which is useful given there is no output schema. But it says nothing about response shape, size, or completeness beyond the topic list.

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 front-loaded with the Korean label before the topic list, which is good. However, the entire content is duplicated across Korean and English, roughly doubling length without adding new information for a single reader.

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 carries the burden of telling the agent what comes back, and the topic inventory does that reasonably well. The only gap is that it does not clarify whether all topics are always returned or whether they are summarized in a fixed format.

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 single optional 'language' enum defaulting to 'ko', fully documented in the schema. The description adds no parameter guidance (e.g., which language to choose for which audience), 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?

It clearly states a specific verb ('get') and resource ('Doply service overview') and then enumerates the exact domains covered (testers, period, devices, pricing, sales channels, org accounts, MCP key). This makes it distinguishable from siblings like get_contact, get_requirements, and search_faq without needing to inspect 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?

The topic list implies when to reach for this tool (pricing questions, device questions, getting an MCP key), but there is no explicit 'use this instead of X' routing against search_faq or get_requirements. An agent must infer routing from the topic list 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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior beyond annotations: that an empty query returns all questions, plus the topical scope of results. It omits result ordering/limits and return shape, keeping it below a 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?

The bilingual pairing is justified for a ko/en/ja tool and the key constraint (empty query lists all) is front-loaded before the topic list. Slightly verbose due to duplicated topic enumeration across both languages, but no wasted sentences.

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 2-parameter, no-output-schema read tool, the description covers what is searched, the topics returned, and the empty-query behavior, which is sufficient to call it correctly. Missing only edge details like result count or ranking, which are minor here.

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% — language is documented in-schema but query is not. The description compensates by defining query's semantics (empty => list everything) and implying it is a free-text search term, which is exactly the missing half. It could add matching behavior (keyword vs fuzzy) for a 5.

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 the Doply FAQ') and enumerates the covered topics (pricing, refunds, SDK requirements, production access), which tells an agent exactly what domain knowledge lives here. It does not explicitly contrast itself with get_requirements or get_service_info, which is the only gap.

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 one concrete usage rule: leaving query empty returns the full question list. However, it gives no guidance on when to prefer this over the sibling tools get_requirements or get_service_info, which plausibly overlap on SDK/requirement topics, so the agent must infer the boundary.

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