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

With no annotations, the description carries the full burden, and it does disclose two useful traits: it operates on an already-stored token (hence zero arguments) and it deliberately does not return the token itself. It does not say what 'validating' yields (a boolean, user identity, an error on expiry) or whether it refreshes the session, which are the details an agent most needs.

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 short sentence, front-loaded with the action and scoped by a clarifying clause. Nothing is wasted, though the extreme brevity means little structure beyond one clause.

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 zero-parameter, output-schema-less tool, the description is minimally adequate: it establishes inputs (none, stored token) and one output constraint (no token returned). The actual return shape on success and failure remains undefined, which is a real gap given no 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?

The tool takes zero parameters, so the baseline is 4. The description correctly signals that no credentials need to be passed because the token is stored.

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 pairs a specific verb (驗證/validate) with a specific resource (the saved Mattermost session token), and '已保存' implicitly separates it from mattermost_login, which presumably acquires a token. It is clear without naming a 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?

There is no explicit when-to-use or when-not-to-use statement, but 'validates the saved token' implies the natural pre-flight use case before calling other Mattermost tools. The agent must infer this rather than being told, and no alternatives are mentioned.

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=false, idempotentHint=false and openWorldHint=true, so the description is not on the hook for the safety profile. It still adds real value beyond them: the requirement for user authorization and the instruction not to blindly resend on timeout — concrete guidance that complements the non-idempotent hint. No mention of what a successful post returns or whether edits/deletes are possible.

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 compact sentence with the action front-loaded and the constraints appended, so no reading time is wasted. Slight redundancy with the schema's message description is the only inefficiency.

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 two-parameter write tool whose annotations cover the safety profile, the description supplies the missing operational context (auth requirement, retry caution, content constraints). The remaining gap is target resolution — nothing explains the channelId or the boundary against reply_to_thread — but this is a minor omission rather than a blocking one.

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%: the 'message' field is already thoroughly documented in the schema, and the description's TL;DR/5-line/50-character rules largely restate it. The 'channelId' parameter carries only a regex pattern with no explanation anywhere, and the description does not clarify that it identifies the target channel or 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 states a clear verb and resource ('發送訊息' / send a message) and identifies the acting identity ('以目前登入者身分'), which the tool name alone does not. It stops short of distinguishing this tool from its closest sibling, mattermost_reply_to_thread, so an agent must infer that this creates a top-level post rather than a threaded reply.

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 implies when the tool applies by describing prerequisites ('須有使用者授權') and a retry rule ('逾時不得直接重送'), and the formatting mandate narrows acceptable input. However, there is no explicit statement of when to prefer mattermost_reply_to_thread or mattermost_get_channel/channel-lookup first, leaving the main selection decision to inference.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the added '唯讀操作' sentence is largely redundant. What does add value is the statement of which fields come back (name, type, archived status), but nothing is said about behavior on an unknown or malformed channel ID.

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, front-loaded with the lookup and the returned fields, with zero filler. Nothing could be trimmed without losing 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 single-parameter read tool whose annotations cover the safety profile, disclosing the returned fields makes it nearly self-sufficient. Minor gaps remain around invalid-ID behavior and whether any team context is included.

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 required parameter with 0% schema description coverage; the only format constraint lives in the pattern field of the schema. The description merely repeats that the input is a channel ID, adding no meaning about expected format or failure modes beyond what the parameter name already conveys.

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 (查詢) and resource (頻道) and even enumerates what is returned (名稱、類型、封存狀態), which distinguishes it from the list-style siblings such as mattermost_list_channels. It does not name a sibling alternative explicitly, so it stops short of a 5.

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

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

The description gives no when-to-use guidance, no exclusions, and no pointer to alternatives like mattermost_list_channels for discovery. Only the 'lookup by ID' framing implies usage; the agent must infer the rest.

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 behavioral burden. It does not state that this is a read-only operation, that it requires an authenticated session, or what happens when no user is logged in, leaving the failure and safety profile undisclosed.

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. It states the resource and scope immediately and nothing in it is redundant.

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

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

For a zero-parameter identity lookup, the description is minimally sufficient, but with no output schema it never indicates what user attributes come back, and it omits the authentication prerequisite that matters for a session-scoped 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. No parameter meaning is missing or contradicted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: retrieving the currently logged-in Mattermost user. It is unambiguous on its own but does not distinguish itself from the close sibling mattermost_auth_status or mattermost_login, which an agent must choose between.

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 auth_status or login, and no stated prerequisite such as an active session. The agent must infer usage purely from the name and the word 'current'.

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 '唯讀操作' (read-only) clause simply restates what readOnlyHint=true and destructiveHint=false already declare, so it earns little credit. What it does add is that the response payload includes channel_id and root_id, which is useful given there is no output schema. It says nothing about error behavior for invalid or unknown post IDs.

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 with no filler, and the core purpose is front-loaded. It is arguably too terse given the undocumented parameter, but nothing written is wasteful.

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 single-parameter lookup with no output schema, the description covers purpose and partially covers the return shape. It is still incomplete on the postId format and on authentication expectations, which matter for an openWorld tool that requires a logged-in session.

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 the single required parameter postId, and the description never explains or even mentions it. The only guidance on format is the 26-character lowercase pattern buried in the JSON schema, so the description fails to compensate for the documentation 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 names a specific verb and resource ('取得單則訊息' — retrieve a single post) and clarifies it returns channel_id and thread root_id. This distinguishes it from sibling tools like mattermost_get_thread and mattermost_search_posts, though those alternatives are never 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?

Usage is only implied: an agent can infer this is for fetching one known post rather than browsing a thread or searching. There is no explicit statement of when to use it versus mattermost_get_thread or mattermost_search_posts, and no mention of prerequisites such as being logged in.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the sentence '唯讀操作' (read-only operation) merely restates the structured data and earns no credit. Nothing is added about reply ordering, pagination or limits on the number of replies returned, or what happens when the post has no replies. For a thread-fetch tool, that behavioral detail matters.

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, with the retrieval scope stated first and the safety note second. There is no filler. The only weakness is that brevity here comes at the cost of the usage and parameter detail noted above.

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 one-parameter read tool with no output schema, the description is minimally adequate: an agent can tell it returns a thread of replies. It omits what the returned thread contains, how replies are ordered, and how to choose this tool over mattermost_get_post, which leaves a real gap for correct tool selection.

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 explain the single parameter, yet it only says '指定訊息' (the specified message), which barely clarifies that postId is a post identifier. The 26-character lowercase alphanumeric format and the fact that the ID must be a post ID rather than a channel or user ID are left to the schema pattern and the agent's inference.

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: fetch the thread and its replies that belong to a given message ('取得指定訊息所屬的討論串及回覆'). This clearly separates it from mattermost_get_post, which returns a single post, and from mattermost_reply_to_thread, which writes. It does not explicitly name those siblings, so the description falls short of the sibling differentiation required for 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 about when to use this tool rather than mattermost_get_post (a single message), mattermost_search_posts, or mattermost_get_channel. The intended use, retrieving a whole thread when you hold a post ID, can only be inferred. Neither prerequisites nor exclusions are mentioned.

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, yet it says nothing about auth requirements (the presence of mattermost_login/mattermost_auth_status suggests sessions matter), whether private/archived channels are included, or whether results are paginated or filtered. Only the read-only nature is implied by the verb.

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 stated up front and no filler. It is efficient, though so terse that nothing beyond the minimum is conveyed.

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 listing tool with no annotations, no output schema, and no pagination or auth disclosure, the definition leaves out nearly everything an agent needs beyond the call signature. It does not describe what a returned channel contains or how large the result set may be.

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%, so teamId is already fully documented as 'Mattermost team ID'. The phrase '指定 team' merely restates that the parameter exists and adds no format, source, or edge-case meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a clear verb+resource ('列出 … channels') scoped to a single team, which an agent can distinguish from mattermost_get_channel (single channel) and mattermost_list_teams (teams). It stops short of naming any sibling, so differentiation is only inferable from the singular/plural 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 when-to-use or when-not-to-use guidance, no mention of a prerequisite team ID obtained from mattermost_list_teams, and no pointer to mattermost_get_channel for single-channel lookup. The agent must infer route selection entirely from the tool name.

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?

Because no annotations are provided, the description must carry the full burden. The phrase 'currently accessible to the user' hints that results are permission-scoped, which is genuinely useful behavioral context. It does not mention pagination, result ordering, failure modes when the user is unauthenticated, or the shape of each returned team.

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 one short sentence with no wasted wording, and the scope qualifier comes before the noun it modifies. The sentence is minimal, but it is not padded; this is a case of appropriate brevity rather than vague 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?

This is a simple zero-parameter listing tool with no output schema, so the bar is lower. Still, an agent cannot tell from the description whether the result is paginated, whether an empty list means no membership, or which identifier it should reuse in later calls.

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?

This tool takes zero parameters, so the baseline score is 4. The description correctly implies that no input is required and that the scope is derived from the authenticated session, indicating there are no filters to apply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (list teams) and scopes it to teams the current user can access. Because it is clearly a list tool, it is distinguishable from siblings such as mattermost_list_channels or mattermost_search_posts. However, it does not state that it is distinct from those 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?

The description gives no guidance on when to call this tool instead of other tools, or what to do afterward. It does not say that the returned team identifiers are needed by channel-related tools, and it gives no prerequisites and no exclusion criteria.

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 at all, the description must carry the full behavioral burden. It does disclose meaningful behavior: a one-time pairing, a session token handed off over SSH to a local Login Helper, and that the provider is decided by the Mattermost site config. It does not say whether the call mutates account/session state, how long the pairing or token lives, or what happens if pairing fails.

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 its return value, then the conditional parameter rule, then the provider note. Dense and purposeful, with no filler, though the provider sentence sits last and reads as an afterthought.

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

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

There is no output schema, and the description does at least say a value is returned (an npx command), which is helpful. But for a login tool with zero annotations, missing side-effect disclosure, token lifetime, and post-login verification steps leaves the agent guessing about what to do once the command is returned.

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

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

Schema coverage is 100% and the sshTarget property already documents 'SSH alias or user@example.com; omit when MCP and browser are on the same machine'. The description's explanation is essentially the same rule restated, adding no new syntax, format, or failure semantics beyond 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 concrete verb and outcome: 'establish a one-time login pairing and return an npx login command'. This is clearly a different action from the sibling mattermost_auth_status, though the description never names that sibling to make the distinction explicit.

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 remote-vs-local condition ('specify sshTarget when MCP is remote, omit when on the same machine') is stated clearly, which is a real usage rule. However, there is no guidance on when to call this at all versus checking mattermost_auth_status first, and no mention of prerequisites or follow-up steps.

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 and destructiveHint=false, so the sentence '非唯讀' earns no credit. Beyond them the description adds real behavior: the server auto-resolves root_id from either a root or a reply post, verifies channel membership, and requires user authorization — all non-obvious and useful. It stops short of saying what happens when the 5x50 limits are exceeded or what the call returns.

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, semicolon-joined clauses with no filler, and the output-format constraint is front-loaded where the agent will see it first. Slightly dense phrasing but nothing wasted.

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

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

For a non-idempotent write tool with no output schema, the definition covers format limits, ID resolution behavior, channel validation, and the authorization prerequisite — enough to call it correctly. The only real gap is failure behavior (limit violations, mismatched channel) and the shape of the response.

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

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

Schema coverage is only 33%, with postId and channelId having no schema descriptions. The description compensates well for postId (accepts root or reply, root_id auto-resolved) and implicitly explains channelId's role via the 頻道歸屬 check. message constraints are fully covered by the schema already, so no further gain there.

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 (回覆) and resource (討論串) plus the output format (TL;DR, 5 lines / 50 chars). An agent can distinguish it from mattermost_create_post by the thread-reply framing, but the description never names that sibling explicitly, so disambiguation is inferred rather than stated.

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 useful preconditions — user authorization is required and postId may be either a root message or an existing reply — which tells the agent when this call is valid. However, there is no explicit when-not guidance and no named alternative (e.g. use create_post for a new top-level message), so routing between siblings is left 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?

No annotations are supplied, so the description carries the full burden. It does disclose one meaningful behavioral trait — results are permission-scoped to the current user — but says nothing about result ordering, limits, pagination, or whether an empty result means no match versus no access.

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 short sentence with no filler, and the permission scope is front-loaded. It is efficiently written but under-specified for a three-parameter search operation, so brevity comes partly at the cost of completeness.

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 annotations, no output schema, and an undocumented boolean, the description should clarify search behavior and result shape; it does neither. An agent can guess how to call it but not what it will get back or how to chain it with mattermost_list_teams for a teamId.

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

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

Schema coverage is only 67%, and the undocumented parameter is the semantically significant one: isOrSearch controls whether terms are OR- or AND-combined, yet neither schema nor description explains it. The description adds no meaning beyond the terms/teamId field hints already in 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?

The description pairs a specific verb ("搜尋") with a specific resource ("Mattermost posts") and adds scope: only posts the current user is permitted to see. This distinguishes it from retrieval siblings such as mattermost_get_post and mattermost_get_thread, though it never names those alternatives 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?

There is no guidance on when to use search rather than fetching a post or thread directly, no mention that a teamId must be supplied, and no hint about how "terms" is matched. The agent must infer all usage context from the name and schema.

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