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

No annotations exist, so the description carries the burden. It does add real value by disclosing that authentication happens with stored credentials and that credentials are never returned, but it says nothing about what a result looks like (success flag, error message, latency) or how failures surface.

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 core action front-loaded and the security constraint trailing. Nothing is wasted, though the 'never return credentials' clause is slightly cryptic in isolation without saying what is returned instead.

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 trivial zero-argument connectivity probe, the definition covers purpose and a key safety property. With no output schema and no annotations, the missing piece is the shape of the response and failure behavior, which an agent would need to act on the result.

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

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

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline for a no-param tool applies. The description correctly implies no arguments are needed.

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 ('Test authenticated IMAP connectivity'), which clearly separates it from the data-retrieval siblings (list_folders, list_messages, read_message) as a health-check tool. It does not explicitly name a sibling, but the purpose is unambiguous.

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 a pre-flight/diagnostic check before attempting folder or message operations, but the description never says when to call it or what to do on failure. No exclusions or alternatives are named.

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

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

With no annotations, the description carries the full burden and does usefully disclose that the operation does not mark messages as read. However, it omits other behavioral details such as whether subfolders are included, permission requirements, pagination, 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 front-loaded sentence with zero wasted words. The key operation and safety behavior are both stated immediately.

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 one-parameter read tool with no output schema, the description is adequate to understand the basic purpose. It is incomplete on folder parameter semantics and on the exact return shape of the counts, which leaves 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?

The only parameter, folder, has 0% schema description coverage, but the description does not explain accepted folder names, path format, or that it defaults to INBOX. It only says 'in a folder' without adding meaning beyond the bare schema property name.

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 specific verb and resource: it counts total and unread messages in a folder. It does not explicitly distinguish itself from siblings like list_messages or search_messages, so it falls short of full sibling differentiation.

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 need folder-level counts rather than message contents. The description adds the safety note 'without marking any read' but gives no explicit when-to-use or when-not-to-use guidance relative to list_messages or search_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?

No annotations are supplied, so the description carries the full behavioral burden. It does add genuinely useful context that results are raw server entries where flags and quoted names may appear unnormalized, which warns the agent not to expect clean display names. It omits any statement about permissions, account/connection requirements, or folder hierarchy/nesting 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?

A single front-loaded sentence with a parenthetical caveat — no filler or redundant restatement of the name. The parenthetical is dense but every clause carries information the agent needs about output shape.

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 parameters, no annotations, and an output schema present, the definition needs little, and the raw-entry caveat covers the main surprise. It still leaves gaps on hierarchy/namespace behavior and on how this differs from folder_status, which matters for selection among five siblings.

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. The schema coverage is also 100%, leaving no semantic 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?

States a specific verb and resource ('List IMAP folders'), which is clearly distinct from list_messages or search_messages. It does not, however, distinguish itself from the sibling folder_status, which an agent could plausibly confuse with this tool.

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 by the name and the word 'List' — the description gives no explicit when-to-use context, no prerequisites, and never names folder_status as the alternative for checking a single folder's 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?

With zero annotations, the description carries the full behavioral burden. It does useful work by disclosing that only headers are returned (not bodies), that results are ordered newest-first by a stable identifier, and that output is capped by a configured maximum. It omits permission requirements, pagination/offset behavior, and what happens when the cap is hit.

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, and the most important constraint (headers only, newest first) appears immediately. The density comes at the cost of leaving out information the agent needs, but no sentence is wasted.

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

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

For a three-parameter read tool with no annotations, no output schema, and 0% schema description coverage, the definition is under-specified: it never says what fields a 'header' contains, whether folder defaults to INBOX, or what unseen_only does. An agent can call it, but only by guessing at the parameters.

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 for three undocumented parameters (limit, folder, unseen_only) and it does not — none of the three is explained, and 'max configured cap' actually obscures the limit parameter by suggesting a server-side cap rather than a caller-supplied value. Baseline for three unlabeled parameters would be a 3; the misleading framing pushes it down.

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 newest message headers') plus the ordering key ('stable IMAP UID'), which lets an agent separate it from read_message (single full message) and search_messages (query-driven). It never names those siblings, so differentiation is inferential rather than 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?

There is no when-to-use guidance at all: no statement of when to prefer this over search_messages for finding messages, and no mention of when the UID ordering matters. The only usage signal is the word 'newest', which implies a recent-inbox browsing scenario.

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 usefully discloses that reading does not mark the message as read, which is an important side-effect clarification. However, it does not cover other behavioral details such as what happens when the UID is missing, whether permissions are required, or how attachments are represented.

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 wording. It conveys the operation, inputs, return content, and a key non-mutating behavior 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?

For a simple two-parameter read tool with no output schema, the description adequately explains what is returned and that the read is non-mutating. It still leaves clear gaps around usage relative to sibling tools and parameter details such as the folder default.

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 description maps both parameters to their purpose: folder and UID locate the message. With 0% schema description coverage, it adds some meaning, but it does not explain the folder default (INBOX) or the UID format and scope.

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: reading a message's text content and attachment metadata by folder and UID. It is clearly a single-message read rather than a list or search, though it does not explicitly name the sibling tools it differs from.

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: read a message when you already know its folder and UID. The description gives no explicit guidance on when to use this instead of search_messages or list_messages, nor any exclusions or prerequisites.

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

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

No annotations exist, so the description carries the full behavioral burden. It does disclose the return shape (headers and UIDs, not bodies), but says nothing about matching semantics (IMAP TEXT covers headers/body, not just subject), result ordering, whether limit truncates silently, or the read-only nature of the call.

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?

One sentence, front-loaded with the verb and resource, with no filler. It is efficient, though the terseness borders on under-specification given four 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?

For a 4-parameter search tool with zero schema coverage and no annotations, the description is thin: scope (folder default, unseen filter), pagination via limit, and match semantics are all left unstated. Only the return shape and the query's plain-text nature are covered.

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 4 parameters. The description clarifies only the required 'query' parameter as plain text matching; folder, limit, and unseen_only are entirely undefined in both schema and description, leaving three of four parameters 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 (search) and resource (mailbox TEXT), plus what comes back ('matching headers and UIDs'). It is distinguishable from read_message, though it never explicitly contrasts itself with the closest sibling list_messages.

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 purpose implies when to reach for it (free-text lookup rather than enumerating or reading a message), but there is no explicit when-not guidance, no mention of list_messages as the alternative for unfiltered listing, and no note about folder scoping.

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