LMGram

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat these. The description adds the context 'linked to the connected account', which is helpful but does not disclose further behavioral traits (e.g., no mention of authentication requirements or rate limits).

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, concise sentence with no wasted words. It is front-loaded and clearly communicates the tool's purpose.

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 has no output schema, and the description does not mention return value contents (e.g., fields like name, email, id). For a simple profile retrieval, this may be sufficient, but the description could be slightly richer to prepare the agent for the 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?

There are no parameters, and schema description coverage is 100% (trivially). The description does not need to add parameter semantics. Baseline 4 is appropriate as the schema already fully covers the absence of 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?

The description 'Returns the LMGram profile linked to the connected account' clearly states the verb (returns) and resource (LMGram profile). The tool is distinct from siblings which deal with matching, messages, and chat, leaving no ambiguity.

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 use when the connected account's profile is needed. No explicit exclusions or alternatives are given, but the context of siblings (list_match_requests, etc.) makes usage clear. A perfect score would require explicit when-to-use or when-not-to-use 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful context about recency and user scoping, but it does not disclose additional behaviors like ordering, pagination, or the shape of the response.

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, well-structured sentence conveys the core action, scope, and filtering options without redundancy or extraneous detail. Every clause 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 read-only list operation with three optional parameters and no output schema, the description covers the key invocation details: what is listed, whose data, and how to filter. It could be slightly more complete by explaining the default response ordering or what a match request contains, but nothing essential is missing for a correct basic call.

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%, so the description needs to compensate. It does clarify that role and status are optional filters, which adds meaning beyond the enum lists, but it does not mention the limit parameter or its role in controlling result size. This is a partial compensation for the low 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 clearly identifies the verb 'Lists', the resource 'match requests', and the scope 'current LMGram user'. It is immediately distinguishable from sibling tools like list_messages and request_human_match by the explicit resource type and read-only intent.

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—whenever a user needs to see their recent match requests—and mentions optional filters. However, it does not explicitly contrast it with sibling tools such as request_human_match or start_chat, nor does it state any conditions where an alternative should be preferred.

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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable context about end-to-end encrypted payloads being represented by a safe placeholder, which is not apparent from the annotations or schema.

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, immediately stating the purpose and adding a critical caveat. No filler or redundancy.

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 simple structure (1 param, read-only, no output schema), the description is mostly complete. It explains the core behavior and the encryption placeholder. However, it does not mention ordering, pagination, or return format, which could be relevant for a list 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 input schema has one required parameter, chatId, with no description. The tool description does not explain what chatId refers to or any format/constraints. With 0% schema description coverage, the description should compensate but does not.

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 'Lists messages in a LMGram chat' with a specific verb and resource. It also adds a useful caveat about encrypted payloads, and it is easily distinguished from siblings like list_match_requests or send_message.

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 explicit guidance on when to use this tool vs alternatives or when not to use it. The description implies it is for viewing chat messages, but does not mention any exclusions, prerequisites, or alternative 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by clarifying the non-effects ('does not publish an intent or send a message') and the per-conversation context isolation, which the annotations cannot express.

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?

Three short sentences, front-loaded with what opens and scoped to the current conversation. Every sentence carries distinct information: purpose, context-isolation rule, and explicit non-effect; nothing is redundant with the title or annotations.

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 zero parameters, rich annotations, and an output schema already present, the description covers everything an agent needs to know before calling it, including the notable fact that it produces no message or intent side effect. The only minor gap is not naming which sibling to use instead when the goal is to send or act, rather than open.

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 for a parameterless tool applies. The schema is intentionally empty (additionalProperties: false), consistent with a pure UI-opening action.

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 ('Open LMGram chats, groups and suggestions for the current ChatGPT conversation'), so the action is unambiguous. The closing clause 'does not publish an intent or send a message' explicitly carves out the behavior of sibling tools like panel_create_intent and panel_send_message, letting an agent distinguish this from the other panel_* tools without opening their schemas.

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 implied by the description ('for the current ChatGPT conversation') and constrained by the guardrail 'never copy a transcript or private documents', which is a real usage rule. However, it never states when to prefer this opener over the other panel_* siblings (snapshot, start_chat, join_group), so the selection guidance is only partial.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful context that the data is authorized and intended for client-side decryption rather than model context consumption. It still does not disclose return format, pagination, or auth flow details.

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 a single front-loaded sentence with no filler, clearly leading with the action 'Retrieve'. The extreme brevity is appropriate for conciseness but borders on under-specification for a tool with three undocumented parameters.

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?

An output schema exists and annotations cover safety, reducing the description's burden. However, all three parameters have 0% schema description coverage, and the description provides no usage criteria or parameter semantics. For a private-chat retrieval tool with required IDs, this leaves substantial 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 description coverage is 0% across all three parameters (contextId, chatId, before), and the description does not mention any of them. With low schema coverage, the description is expected to compensate, but it provides no parameter meaning or format guidance.

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 gives a clear verb and resource: retrieve authorized chat data for client-side decryption. It also distinguishes the output from model context, which helps separate it from general message-reading tools. However, it does not explicitly name or differentiate from siblings like list_messages or panel_snapshot.

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 'not model context' implies a usage boundary, but the description gives no explicit when-to-use guidance, prerequisites, or alternatives. An agent must infer when this tool is appropriate versus list_messages, panel_snapshot, or other panel 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?

Annotations already disclose write/open-world/non-idempotent/non-destructive behavior, so the bar is lower. The description adds useful content restrictions (only minimized user-reviewed intent, no secrets or private transcripts), but does not explain what happens after publishing or visibility consequences.

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 core action and constraints, with no wasted wording. Size is appropriate for the tool's narrow purpose.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, with 0% schema description coverage across five parameters, the description fails to document essential input semantics, making it incomplete 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 0% for 5 parameters (contextId, topic, summary, need, language). The description provides no parameter-level meaning, so an agent cannot infer what to supply for each field.

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 ('Publish') and resource ('minimized intent explicitly reviewed and submitted by the user'), making the action clear. It does not explicitly contrast with sibling tools, but the resource 'intent' is distinct from chat/message/group 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?

It gives a clear condition for use ('only the minimized intent explicitly reviewed and submitted by the user in this conversation panel') and explicit content exclusions ('Do not include secrets, private transcripts, or dating requests'). It stops short of naming alternative tools for other scenarios.

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 destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds the useful constraint that the suggestion must be unopened, but it does not explain what decline actually does to the suggestion or whether it is reversible. No contradiction with annotations exists.

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 with no wasted words. It is very concise, though arguably too terse for a destructive tool that requires two opaque IDs, which keeps it from a perfect score.

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?

Despite rich annotations and an output schema, the description is incomplete for a two-parameter destructive mutation. It provides no parameter semantics, no usage context relative to siblings, and no details about side effects beyond the unopened qualifier.

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 0% for two required parameters (contextId and matchRequestId), and the description does not mention or explain either parameter. With no parameter meaning provided anywhere, the definition fails to help an agent supply correct values.

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 (Decline) and resource (match suggestion), plus a state qualifier (unopened). It does not explicitly differentiate from sibling tools like panel_snapshot or panel_mark_read, but the purpose is clear on its own.

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 when-to-use versus alternatives guidance, no prerequisites, and no exclusions. The agent must infer that this is for declining a suggestion that has not been opened, but no routing information to sibling tools is provided.

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 disclose the mutation profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true), so the description needn't restate safety. It adds almost nothing beyond them: no behavior when no invitation exists, no auth or permission requirements, no side effects on other members or state.

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 no waste, appropriate for a simple action tool. It is arguably too terse given the two undocumented parameters, but there is no filler or redundancy.

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?

An output schema exists so return values needn't be described, but the description leaves key operational gaps: the meaning of both required parameters, the precondition of a pending invitation, and the resulting state after joining. For a two-parameter mutation tool this is under-specified.

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?

Both required parameters (contextId, roomId) have 0% schema description coverage, and the description mentions only an unspecified 'context' without connecting it to contextId or explaining that roomId identifies the group. With two undocumented required parameters, the description fails to compensate for the schema gap.

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: 'Accept an existing group invitation.' An agent can tell it joins a group rather than sending a message or listing requests. It does not, however, name or differentiate itself from any sibling beyond the panel_ prefix context.

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 guidance on when to use this tool versus alternatives, and no stated prerequisite that a pending invitation must already exist. The qualifier 'existing' hints at a precondition but never spells it out, leaving the agent to infer when this call is valid.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=true, covering the safety and repeatability profile. The description adds only "the displayed" scoping and says nothing about the state change (read marking), whether it is visible to other participants, or auth requirements.

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 no filler or redundancy. It is appropriately compact, though extremely minimal given the tool's undocumented parameters.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. However, for a mutation tool with two entirely undocumented required parameters, the description is too thin to let an agent call it confidently.

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 0% for two required parameters, so the description must carry the burden, and it does not. It gives no indication of what chatId or contextId mean or how the 43-character contextId relates to the chat, leaving both parameters fully opaque.

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 ("Mark ... as read") and scopes it to "the displayed chat," which is clear enough to distinguish it from write-oriented siblings like panel_send_message. It stops short of naming or contrasting any sibling explicitly, so it does not reach 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?

There is no guidance on when to call this versus alternatives, no prerequisites, and no exclusions. An agent must infer that it should be used after viewing a chat to clear the unread state.

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 idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds one security-relevant constraint beyond the annotations: only the public key is registered. It says nothing about auth requirements, error behavior, or what happens on re-registration.

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 no filler; the key constraint leads. It is arguably too terse for a 3-parameter cryptographic operation, but there is no wasted wording.

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?

An output schema exists so return values need not be described, but with 0% schema coverage the description should compensate for undocumented parameters and the public-key format. An agent cannot confidently call this without guessing what contextId and deviceId should contain.

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 0% and all three parameters are required, yet the description explains none of them. It hints that publicKey is a public key, but deviceId and the rigid 43-character contextId are left entirely unexplained, including expected encodings.

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 ('Register') and resource ('public encryption key ... for this user's panel'), which is clear on its own. However, it does not distinguish itself from the sibling panel_sync_device_keys, which sounds like it may also register device key material.

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 statement of when to use this versus panel_sync_device_keys or panel_start_chat. The word 'only' hints that private key material must not be sent, but that is an inference, not 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?

Annotations declare idempotentHint=true, but the description adds the crucial qualifier that a retry is only safe with the identical payload and clientMessageId, correcting a naive reading of the annotation. It still omits auth requirements, failure modes, and any note on the open-world (server-forwarding) behavior flagged by openWorldHint.

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 tightly written sentences with zero filler; the destructive action is named first and the retry constraint second. Nothing is wasted or buried.

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 an 8-parameter, all-required, nested-schema mutation tool with 0% parameter documentation, the description is far too thin: it never explains encryptionScheme, encryptionNonce, encryptedKeys, senderDeviceId, or the contextId/chatId distinction. The existing output schema excuses it from describing return values, but the input-side gaps are substantial.

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 0% across 8 required parameters, including a nested encryptedKeys map, so the description must carry the burden and largely does not. It earns partial credit only by implying clientMessageId functions as the idempotency key, which is real semantic information the schema (a bare string) does not convey.

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 client-encrypted text message), which is clearer than the generic sibling 'send_message' and 'panel_chat'. It does not, however, explicitly distinguish the panel_ variant from the plain send_message sibling, leaving the agent to infer the difference.

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?

Gives genuine timing guidance (send only after the user presses Send) and a retry rule, which is useful operational context. It offers no when-to-use / when-not-to-use comparison against the sibling send_message, so usage is only partially covered.

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 non-open-world, so the safety profile is covered. The description adds only the 'private panel data' scoping, which hints that refresh is scoped to this conversation rather than global. It does not say whether refresh re-fetches state, triggers a server-side sync, or returns a snapshot, and does not contradict the readOnly hint.

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 compact sentence with the scope front-loaded and zero filler. It is efficient, though the brevity edges toward under-specification rather than true conciseness.

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?

An output schema exists so return values need not be described, and annotations carry the safety profile. However, for a tool that requires an opaque 43-character contextId, the description supplies no usage trigger and no parameter meaning, leaving the calling agent with meaningful 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 description coverage is 0% and the single required parameter contextId is undocumented in both schema and description. The 43-character length constraint strongly suggests a structured key, but the description offers no meaning, format, or source for it, so it fails to compensate for the coverage gap.

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 has a verb ('Refresh') and a scoped resource ('this conversation's private panel data'), so the general intent is inferable. But 'private panel data' is ambiguous about what is actually refreshed or returned, and the name panel_snapshot vs. title 'Refresh conversation' do not cohere. It also does not distinguish itself from the many panel_* 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?

There is no indication of when this tool should be used versus siblings like panel_chat, panel_sync_device_keys, or list_messages, nor any prerequisite or trigger condition. The agent is left to infer usage entirely.

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, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds one behavioral detail: the request avoids a plaintext introduction, but it does not explain permissions, side effects, or what a successful request triggers.

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 with no filler. It is concise, though its brevity contributes to ambiguity rather than precision.

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?

Although an output schema exists, the description does not compensate for undocumented required parameters, lacks usage guidance, and gives minimal behavioral context for a non-read-only tool. It is not sufficient for an agent to invoke confidently without opening the schema.

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 0% for two required parameters. The description only loosely hints at contextId ('in this context') and matchRequestId ('with a suggestion'), without explaining formats, constraints, or how the IDs are obtained.

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 an action ('Request a chat') and a context ('in this context'), but 'with a suggestion' is vague and it does not distinguish this from siblings such as start_chat or panel_chat. An agent can infer the general purpose but not the precise distinction.

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 explicit guidance on when to use this tool versus start_chat, panel_chat, or request_human_match. The phrase 'without sending a plaintext introduction' describes a constraint, not a routing condition.

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 the mutation/idempotency/open-world safety profile, so the bar is lower. The description adds genuinely useful security context: it transmits only client-encrypted keys, never messages, plaintext, or private keys, to registered devices only. It still omits auth requirements or any failure/rate-limit behavior, keeping it from 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?

Two tight sentences, front-loaded with the core action and followed by the key negative guarantees. Every clause earns its place 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?

An output schema exists, so return values need no explanation, and the privacy scope is well covered. However, for a 4-parameter required payload with 0% schema description coverage, the description leaves an agent without enough to populate the inputs confidently, which is a clear completeness 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?

Schema description coverage is 0% and all four required parameters (contextId, chatId, sourceDeviceId, updates) are undocumented. The description characterizes the payload abstractly ('client-encrypted message keys') but says nothing about the meaning, format, or constraints of contextId, sourceDeviceId, messageId, or encryptionNonce, so it barely compensates.

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 (share/sync) and resource (client-encrypted message keys) scoped to the account's own registered devices. It also carves out what it is not (not a message send), which helps separate it from the many send_message/panel_send_message siblings. It stops short of naming a specific alternative, so a 4 rather than 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?

There is a scoping constraint ('only with this account's registered devices'), which implies the device-key-sync scenario, but no explicit when-to-use, prerequisites, or routing to/from the numerous sibling panel_* tools. An agent gets no guidance on when this is the right call versus e.g. panel_register_device or panel_send_message.

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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description reveals important behavioral constraints: it is opt-in, excludes romance/dating, and prohibits sensitive data like secrets or API keys. This adds privacy/trigger context not captured in annotations. It doesn't contradict annotations, though it could further clarify side effects (e.g., persistence or notification).

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?

Three compact sentences, front-loaded with the core purpose, then usage boundaries and data-safety instructions. Every sentence adds value 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?

The description nails the trigger and safety constraints, but with 8 parameters and no output schema, it leaves gaps: no explanation of matchType/sensitivity/maxCandidates, and no indication of what the response/result looks like or next steps. It is adequate for a well-scoped tool but not fully 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 38%, with descriptions for need, topic, and summary but no descriptions for urgency, language, matchType, sensitivity, or maxCandidates. The description repeats some schema constraints (non-sensitive summary, no dating) but adds no new meaning for the five undocumented parameters, so it doesn't compensate for the low 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 clearly states the tool creates an 'opt-in LMGram human match request' and specifies the exact trigger ('only after the user explicitly asks to use LMGram to find a collaborator, peer, mentor, or helper'). It distinguishes itself from sibling tools by focusing on match requests rather than messages/chats, and explicitly excludes dating/romantic use.

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 explicit when-to-use guidance ('only after the user explicitly asks'), clear exclusions ('Never invoke for general advice, dating or romantic matchmaking'), and even instructs on the preprocessing step ('ask for a minimized non-sensitive summary first'). This goes beyond a general hint and gives actionable direction.

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 indicate mutation (readOnlyHint=false) and non-destructiveness. The description adds no further behavioral context, such as side effects, authorization needs, or rate limits.

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, concise sentence that is front-loaded with the key action. No redundant words or unnecessary detail.

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 tool's simplicity and lack of output schema, the description is too sparse. It omits parameter explanations and any context about message limits, formatting, or expected 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?

The input schema has 0% description coverage, and the description does not explain the purpose or format of chatId or body. The agent receives no guidance on parameter values.

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 'Sends a message into a LMGram chat,' specifying the action (sends) and the resource (message into a chat). It effectively distinguishes from sibling tools like list_messages and start_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?

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or context for invocation.

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 indicate the tool modifies state (readOnlyHint=false) and is non-idempotent, but the description adds minimal behavioral context beyond 'starts a chat'. It does not describe side effects, state requirements, or error conditions. Acceptable given annotations, but could be more informative.

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?

Single sentence is concise and front-loaded. However, the phrase 'or records that this side wants to chat' is somewhat redundant and could be split for clarity. Still, 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 the absence of an output schema, the description should clarify what the tool returns or what side effects occur (e.g., whether a chat is created immediately or a request is queued). The ambiguity about 'records' versus 'starts' leaves the behavior unclear 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 coverage is 50% with only 'body' described. The tool description adds no information about parameters, especially the required 'matchRequestId', leaving its purpose ambiguous. The description should clarify what a match request ID represents and how to obtain it.

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 it starts a chat for a match request, which distinguishes it from sibling tools like 'send_message' or 'list_messages'. However, the addition 'or records that this side wants to chat' introduces slight ambiguity about whether it always creates a chat or just logs intent.

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 explicit guidance on when to use this tool versus alternatives like 'send_message' or 'request_human_match'. The context of being for a match request is implied, but without exclusion criteria or prerequisites.

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