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

No annotations are supplied, so the description carries the full burden. It does disclose that the operation is dry_run-able and that preset controls room visibility (public vs private), which is genuine behavioral context, but it says nothing about required permissions, whether invites notify users, or what side effects occur on creation.

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 with the core action front-loaded and zero filler; the preset list and id format are the two facts an agent most needs. Slightly terse at the cost of the undocumented parameters, but structurally sound.

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 the description covers the highest-risk parameters (preset, invites, dry run). Still, for a 7-parameter mutation tool with no annotations and 0% schema coverage, four parameters and all permission semantics are left to inference.

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 7 parameters, so the description must compensate. It covers preset (values plus default) and invite_user_ids (required @user:server.tld format), and touches dry_run, but leaves name, topic, tenant, and is_direct entirely undocumented 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?

States a specific verb and resource ('Create a new Matrix room') that no sibling shares — every sibling is a read/send/list/invite tool, so the create action is unambiguous. An agent can identify the tool without opening the 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?

Usage is implied by the verb and by the absence of any sibling that creates rooms, and the preset enumeration hints at the intended privacy modes. However there is no explicit when-to-use/when-not guidance and no mention of prerequisites such as being joined to a homeserver or tenant scoping.

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 behavioral burden and does well: it discloses result ordering, the cursor-based pagination protocol, and the important E2EE caveat that rooms surface ciphertext. It omits auth/permission requirements and rate limits, which is the main remaining gap.

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 the tool returns and immediately followed by the pagination mechanic and the E2EE caveat. Every sentence adds information; no padding.

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 the description covers ordering, paging, and the encryption caveat. The main omission is the meaning of the tenant and limit parameters for a tool with no annotations backing it up.

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%, so the description must compensate and it only partially does: before_cursor is explained well, including its link to the returned next_cursor value. limit, tenant, and room_id carry no semantic detail in either the schema or the description.

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 ('Most recent messages in a room') plus the ordering ('newest first'), so the agent knows exactly what it retrieves. It does not explicitly contrast itself with matrix_search_messages, but the 'recent' framing makes the distinction reasonably 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 explains how to page backward (feed next_cursor back as before_cursor), which is genuine operational guidance. It never says when to choose this over matrix_search_messages or other read tools, nor any prerequisites, so usage is only implied.

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, yet it says nothing about read-only status, permissions, rate limits, or side effects. It merely lists output fields.

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 very short but is an unstructured fragment that omits the core action. It is under-specified rather than appropriately concise.

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 already exists, so listing return fields adds little value. The description omits purpose, usage context, and parameter meaning, making it inadequate 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%, and the description does not mention the required room_id or the optional tenant parameter. It fails to compensate for the undocumented 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 is a fragment listing returned fields rather than stating what the tool does. It does not name a verb or explain that this retrieves room metadata, leaving the action to be inferred from the tool name.

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 siblings like matrix_list_joined_rooms or matrix_list_room_members. The description gives no context, exclusions, or alternatives.

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. It does add genuine behavioral information: the operation is a mutation and supports a dry-run mode, which is valuable for an agent deciding whether to preview effects. It omits, however, authorization/power-level requirements, idempotency (re-inviting an already-joined user), and failure behavior.

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 with the core purpose front-loaded and no wasted words. The coined term 'dry_run-able' is compact but slightly informal/obscure compared to stating the parameter explicitly, which keeps it out of 5 territory.

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?

This is a mutation tool with no annotations, 5 parameters at 0% schema coverage, and no stated permission requirements. Although an output schema exists (so return values need not be explained), the description leaves too much unspecified for an agent to invoke it confidently beyond the happy path.

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 5 parameters. The description compensates for exactly one of them, giving the user_id format with a concrete example ('@alice:example.org'), and gestures at dry_run via 'dry_run-able'. room_id format, reason, and tenant are entirely undocumented in both description and 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 states a specific verb and resource: 'Invite a user to an existing room.' This clearly distinguishes it from every sibling (list, get, send, create, search), so an agent can select it without ambiguity. It stops short of a 5 only because it doesn't name or contrast a specific sibling alternative.

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?

'to an existing room' implies the precondition that the room must already exist, and 'dry_run-able' hints that a safe trial mode is available. However, there is no explicit when-to-use/when-not-to-use guidance, no mention of the required room permission/power level, and no routing to 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?

With no annotations, the description carries the full behavioral burden. It does disclose useful traits: pagination via cursor, the tenant defaulting rule, and the fields returned. It omits any statement about permissions/auth needed to list joined rooms or what happens on invalid tenant.

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?

Short and front-loaded, with the core purpose first and operational notes after. The telegraphic fragments ('Homeserver to target.', 'Cursor-paginated.') are terse but each carries 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?

For a simple read-only list tool with an output schema present, the description covers purpose, pagination, and tenant selection. The main gap is the undocumented 'limit' parameter, which is minor given the output schema exists.

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 0%, so the description must compensate. It handles 'tenant' well (what it targets, the default-omit behavior, and the available values) and gestures at 'cursor' through the pagination note, but 'limit' is never explained and cursor's integer-offset semantics are left to 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?

States a specific verb and resource ('List rooms the configured account has joined') and even previews the returned fields (name, topic, encryption flag). It is clearly distinguishable from siblings like matrix_get_room_info or matrix_list_room_members by resource scope, but it never explicitly contrasts itself with them.

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: the agent can infer this is the tool for enumerating joined rooms, and 'Cursor-paginated' hints that repeated calls may be needed. There is no explicit when-to-use/when-not guidance or mention of alternative tools such as matrix_search_messages for finding a room.

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 behavioral burden. It usefully discloses that results are paginated and what fields come back, but says nothing about permission requirements (must the caller be joined?), how 'joined' differs from invited/banned members, or ordering guarantees.

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 dense sentence with the resource, scope, return fields, and pagination behavior front-loaded; no filler or repetition.

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 explaining return values is not required (though it does). What remains missing for a 4-parameter, annotation-free tool is tenant semantics and any access-condition context.

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 four parameters, so the description must compensate and largely does not. It implies room_id and the pagination pair (limit/cursor) but leaves the tenant parameter and cursor's integer-vs-opaque semantics completely unexplained.

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 (list), resource (room members), and scope (joined members), plus the returned fields (user_id + display name). It is clearly distinguishable from the sibling matrix_list_joined_rooms (rooms the user belongs to), but never names that sibling explicitly.

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 when-to-use guidance, no prerequisites, and no mention of alternatives among the ten siblings. The agent must infer from the name alone that this is the membership-listing call rather than the room-listing call.

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 present, so the description must carry the behavioral burden. It states the mutation and the inclusive range ('up to and including'), but omits side effects, authentication requirements, idempotency, and whether this triggers notifications—significant gaps for a state-changing operation.

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 states the action and its scope with no filler. Every word earns its place, and the inclusive boundary is conveyed efficiently.

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 an output schema that relieves return-value explanation, the description is incomplete for a 3-parameter mutation tool with no annotations and no parameter descriptions. It omits the tenant parameter, usage context, and behavioral details, leaving the agent with 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%, so the description must compensate. It implicitly maps 'room' to room_id and 'given event' to event_id, but never mentions the 'tenant' parameter and adds no format or syntactic detail beyond the schema's type 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?

States a specific verb ('Mark...as read') and resources ('room', 'event'), making the purpose unambiguous. However, it does not mention sibling tools or explicitly distinguish itself from the other room- and message-related tools, 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?

Provides no guidance on when to use this tool versus alternatives, no prerequisites such as required permissions, and no exclusions. It is not misleading, but the agent receives no routing 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?

No annotations are provided, so the description carries the full burden. It usefully discloses one real behavioral constraint — encrypted rooms are not searchable server-side — but says nothing about auth scope, pagination/limit behavior, or result ordering.

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 with zero filler; the primary scope statement comes first and the caveat second. 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?

An output schema exists, so return values need not be described, and the search scope plus encryption limitation are covered. The undefined tenant parameter is the main remaining gap for a non-mutating search 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 description coverage is 0% across four parameters, so the description must compensate and largely does not. It explains the effect of room_id and implies search_term, but limit and tenant are left entirely undocumented.

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 ('full-text search across joined rooms') plus a scoping modifier for room_id. It implicitly separates itself from sibling reads like matrix_get_recent_messages, though it never names an alternative explicitly.

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 parenthetical explains the room_id branch (one room vs all joined rooms), which implies when to narrow the query. There is no explicit when-to-use/when-not guidance and no named alternative to fall back on for listing recent messages.

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 behavioral burden. It does disclose the msgtype 'auto' inference rule and that a dry run is possible, which is genuinely useful, but it omits permission/size limits on uploads, what dry_run actually returns, and the role of idempotency_key for a mutating send.

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 the core action and followed by the two most non-obvious parameter notes. Nothing is padded, though the fragment 'dry_run-able' is terse to the point of being cryptic.

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, and the msgtype inference is covered. However, for an 8-parameter mutation tool with zero annotation and schema-description coverage, the missing explanation of idempotency_key, tenant scoping, and dry_run behavior leaves real 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 0%, so the description must compensate and it only covers three of eight parameters: file_b64's base64 encoding, msgtype's 'auto' inference against mime_type, and a passing mention of dry_run. tenant, idempotency_key, room_id, and filename receive no explanation at all.

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 a specific verb and resource: 'Send a file attachment to a room,' which clearly distinguishes it from a text-sending tool. It does not name the sibling matrix_send_message or explain the boundary between the two, so a 5 is not warranted.

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 (use this when you have file bytes to post), and 'dry_run-able' hints at a preview path, but the description never states when to prefer this over matrix_send_message or what preconditions exist. No exclusions or alternatives are given.

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 and does well on the risky parts: dry_run is explicitly non-sending, and idempotency_key is disclosed as being forwarded as the Matrix transaction ID with duplicate-suppression semantics on retry. It omits permission/membership requirements and rate-limit behavior, so it is not complete, but the mutation-safety disclosure is above average.

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 tight sentences, no filler, with the core action stated first and the two behavioral caveats following in order of likely relevance. Every sentence 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?

An output schema exists, so return values need not be explained, and the description adequately covers the send/preview/retry paths of a mutation tool. It falls short on the unexplained tenant parameter and the complete absence of permission or membership preconditions expected for a room-scoped write.

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 5 parameters, so the description must compensate. It meaningfully explains body (plaintext content), dry_run, and idempotency_key, but leaves room_id and especially tenant completely undefined — the agent cannot tell what tenant scoping does or what value to pass.

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 plaintext message to a room"), and the word "plaintext" implicitly distinguishes it from matrix_send_file and matrix_send_reaction. An agent can identify the correct sibling without opening 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 description gives conditional guidance for two parameters (dry_run for previewing, idempotency_key for retries), which is genuine usage context. However, it never states when to prefer this tool over matrix_send_file for attachments or matrix_send_reaction, nor any prerequisite such as room membership.

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 full burden. It helpfully discloses the stacking behavior ('stacks alongside other reactions, doesn't replace') and that it's dry_run-able, which are real behavioral traits. However it omits permission requirements, idempotency behavior, and any rate-limit 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?

Three short, front-loaded sentences with zero filler. The core action, the key behavioral fact, and the dry_run hint are all packed tightly.

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 explained. But with 6 params, 0% schema coverage, and no annotations, the description leaves material gaps around idempotency_key, tenant, and permission expectations.

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%, so the description must compensate but largely doesn't. It conveys what 'emoji' takes and that a target message is required, plus dry_run, but gives no meaning for tenant, idempotency_key, or room_id, leaving half the parameters undocumented anywhere.

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+resource+scope: adding an emoji reaction to an existing message, with concrete emoji examples. The 'existing message' framing distinguishes it implicitly from matrix_send_message, though no sibling is named explicitly.

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 'to an existing message' implies the precondition (target must already exist), and 'dry_run-able' hints at a preview mode. But there's no explicit when-to-use vs matrix_send_message/matrix_mark_read guidance or when-not conditions.

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