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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it delivers almost nothing. It does not say the default action moves to Trash rather than deleting permanently, nor whether the operation is reversible or requires special permissions — the only signal on that comes from the schema's parameter descriptions.

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 single sentence is front-loaded and free of waste, but for a destructive, multi-parameter tool with no annotations it is under-specified rather than genuinely concise. The brevity leaves useful context unstated.

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 schema fully documents all three parameters. What remains thin is the description's coverage of the destructive semantics and the absence of any guidance against sibling tools, leaving completeness merely adequate.

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 100%, and the schema already documents message_id, folder (default 'INBOX'), and permanent (trash vs. expunge) thoroughly. The description adds no parameter meaning beyond that, which is the expected baseline when the schema does the heavy lifting.

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 ('Delete an email message'), so the agent knows exactly what operation this performs. However, it offers no differentiation from siblings like move_email, which can also remove a message from a folder, leaving the agent to infer the 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 guidance on when to use this versus alternatives such as move_email, nor any mention of prerequisites or the trash-vs-permanent decision at the usage level. The agent must derive the workflow entirely from the schema.

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. 'Forward' implies a send/mutation, but there is no disclosure of permissions, side effects, whether the original sender is visible, or what new message gets created.

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 wasted words. It is appropriately sized for a simple action, though it borders on under-specification rather than over-verbosity.

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 is simple and has an output schema, so return values need not be explained. However, with no annotations and no usage or behavioral context, the description leaves gaps for a mutation tool that sends email; it is minimally adequate 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 100%, so parameters (message_id, to, folder, attachments, additional_message) are fully documented in the schema. The description adds no parameter details beyond what the schema already provides, making the baseline 3 appropriate.

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 (Forward) and resource (existing email) with target (new recipients). It is clear and distinct from send_email and reply_email by implication, but it does not explicitly distinguish itself from siblings or name alternatives.

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 or alternatives are given. An agent can infer it is for forwarding, but the description does not say when to prefer it over send_email/reply_email or any 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 are provided, so the description carries the full burden of behavioral disclosure. 'Download/extract' implies a read operation, but nothing is said about authentication needs, attachment size limits, what happens with multiple matches, or how the payload is delivered (binary vs. saved file), which matters for a download tool.

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 the action verb and resource stated first and zero wasted words. Appropriate length for a simple retrieval tool.

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 schema fully covers parameters. However, for a tool requiring a message_id that must be sourced elsewhere, the absence of any prerequisite or workflow guidance leaves a small but real 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 100%, and all three parameters (folder, message_id, attachment_name_or_index) are documented in the schema itself. The description adds no extra meaning beyond the schema, 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 states a specific verb ('download/extract') and resource ('attachment from an email message'), which cleanly separates it from every sibling, none of which deal with attachments. It stops short of a 5 only because it doesn't contrast itself with alternatives (e.g. read_email) the way a maximally differentiated definition would.

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, no prerequisites (e.g. that a message_id must first be obtained via list_emails/search_emails), and no stated alternatives. The usage is only vaguely implied by the tool name and description.

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 disclosure burden. The verb "Get" implies a read-only summary and the content enumeration is benign, but permissions, auth requirements, and side effects are never addressed beyond the implicit safe-read framing.

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 verb and resource, then the return contents. No filler or repetition; 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 zero-parameter status tool with an output schema present, the description is essentially sufficient—return fields are even summarized, which the output schema would cover anyway. Only the absent usage framing keeps it from being 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?

The schema declares zero parameters, so per the baseline rule there is nothing for the description to compensate for. No parameter-level ambiguity exists.

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 ("Get the overall status of your METU Webmail account") and enumerates the returned content, which implicitly separates it from the granular siblings list_folders/list_emails. It is clear what it does, though it never names an alternative to sharpen the boundary.

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, no prerequisites, and no reference to alternatives such as list_folders or list_emails. An agent can infer this is an account-overview call, but nothing in the text tells it when this is preferable.

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. 'Recent' is the only behavioral hint and it is undefined (how recent? sorted how?). Nothing is said about pagination behavior, permissions, rate limits, or ordering, which matters for a listing tool with offset/limit parameters.

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 clean sentence with the action front-loaded and zero filler. It is efficient, though its brevity contributes to the thin guidance elsewhere.

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 a full output schema, return values need not be explained, and the 100%-covered input schema handles parameters. The remaining gap is routing guidance relative to search_emails and read_email, which the description never addresses.

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 100%, so the schema already documents limit, folder, offset, and unread_only in detail. The description adds no semantics beyond what the schema provides, 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 uses a specific verb (List) and resource (emails) and scopes it to a mailbox folder, so the core action is unambiguous. However, it does not distinguish itself from the closely related siblings search_emails or read_email, leaving the agent to infer the boundary.

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 versus search_emails (filtered query) or list_folders, nor any stated prerequisites or exclusions. Usage is only implied by the phrase 'recent emails from a specific mailbox folder'.

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 burden; it implies a side-effect-free read via 'List all available' but never states it explicitly, and says nothing about permissions or whether folders can change between calls. For a trivial no-parameter read, the implied semantics are adequate, but it stops short of explicit behavioral disclosure.

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 action and resource. The second sentence enumerates return fields that the existing output schema already covers, making it mildly redundant rather than 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?

An output schema exists, so the description need not explain return values, and for a zero-parameter read tool this is close to complete. The only real gap is the missing when-to-use versus the sibling mailbox-status/listing tools.

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 convey and the baseline is 4. The schema coverage is 100% and the empty schema matches the description's claim of a full listing.

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?

Names a specific verb and resource ('List all available email folders and mailboxes') and scopes it to a METU Webmail account, so the agent knows exactly what it retrieves. It does not distinguish itself from nearby siblings like get_mailbox_status, which a zero-param folder lister plausibly overlaps with, but the core 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?

The description never says when to call this versus get_mailbox_status, list_emails, or search_emails, nor does it state any precondition. For a tool whose sibling set contains another mailbox-status tool, that omission leaves real routing ambiguity.

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 falls short: it does not say the change is persisted server-side, whether it is reversible, whether unmentioned flags are left untouched, or whether any special permissions are required. 'Update' signals mutation but nothing about side effects or failure modes is disclosed.

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 efficient sentence with the verb front-loaded and zero padding. The hedged 'such as' phrasing slightly weakens precision but costs nothing in length.

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 flag-mutation tool with a fully documented schema and an output schema (so return values needn't be described), it is close to adequate. It still omits the important behavioral detail that null flag parameters mean 'no change' and says nothing about error conditions or idempotency.

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 100%, so the baseline is 3. The description adds a small amount of value by mapping natural-language flag concepts (read/starred) onto the is_read/is_flagged parameters, but it does not explain the null default semantics (null = leave unchanged) or the folder default, which the schema already covers.

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 ('Update email flags') and enumerates the concrete flag operations (read/unread, starred/flagged), so an agent can distinguish it from siblings like move_email or delete_email. It does not explicitly name which sibling to use instead, but the resource is distinctive enough 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?

There is no statement of when to use this tool versus alternatives, and no prerequisites (e.g., that the message must already exist, or how it differs from read_email which presumably also marks as read). Usage is only implied by the operation 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?

With no annotations, the description carries the full burden but only states the move operation. It omits key behavioral traits such as permissions needed, whether the move is reversible, and the significant default target of 'Trash' (which makes a bare call behave like a deletion).

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 efficient, though extremely minimal.

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 and the input schema is well documented, the tool is a mutation with no annotations. The description fails to mention the critical default behavior (moving to 'Trash') or side-effect context, leaving it incomplete for safe 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 100%, so the schema already documents message_id, source_folder, and target_folder including defaults. The description adds no parameter meaning beyond what the schema provides, 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 states a specific verb ('Move') and resource ('an email') and the folder-to-folder action. It does not, however, explicitly differentiate from siblings like delete_email or mark_email, 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?

There is no when-to-use guidance, no exclusions, and no mention of alternatives such as delete_email or mark_email. The operation is only implied by the verb.

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 omits a meaningful side effect: mark_as_read defaults to true, meaning this 'read' operation mutates mailbox state (marks the message Seen) unless overridden. Permissions, error behavior on a bad message_id, and the side effect of reading are all 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 focused sentence with no filler, and the purpose is front-loaded. It is efficient, though arguably too thin given the side-effect behavior it leaves unstated.

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. However, with zero annotations and a default-true mutation (mark_as_read), the description should disclose the state-changing side effect and permission expectations to be fully adequate.

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 100%, so all three parameters (folder, message_id, mark_as_read) are already documented in the schema, including defaults. The description adds no parameter meaning beyond what the schema provides, so the baseline of 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 states a specific verb+resource ('Read the full content and details of a specific email message'), which is unambiguous. However, it does not distinguish itself from siblings such as list_emails or search_emails; the required message_id in the schema implies the distinction, not the description itself.

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 search_emails or list_emails, nor any prerequisites or exclusions. The only hint of usage context ('from list_emails or search_emails') appears in the schema parameter description, not in the tool description.

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 disclose meaningful automatic behavior: 'Re:' prefix handling, In-Reply-To/References headers, recipient selection, and quoting the previous message. It stops short of stating that the reply is actually sent, any auth requirements, or irreversibility, which keeps 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 sentences, zero waste, with the core action front-loaded and the automatic-handling details following. 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?

Output schema exists so return values need not be explained. For a mutation tool with no annotations, the description covers the reply-construction behavior well, but omits whether the message is dispatched immediately and any permission requirements, leaving a small 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 100%, so all six parameters (including folder default, reply_all, attachments) are already documented in the schema. The description's mention of 'recipient selection' loosely relates to reply_all but adds no syntax or format detail beyond the schema, so the baseline of 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?

States a specific verb (reply) and resource (existing email message), which clearly differentiates it from send_email and forward_email in the sibling list. Missing an explicit sibling contrast, but the action 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 implied by 'reply to an existing email message' — an agent can infer this is for responding to a received message rather than composing or forwarding one. However, no explicit when-to-use guidance or comparison to send_email/forward_email 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?

No annotations are provided, so the description carries the full burden. 'Search' weakly implies a read-only, non-destructive operation, but the description discloses nothing about result ordering, pagination beyond the limit default, or whether unset filters broaden or narrow results.

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 zero padding. It is efficient, though the brevity is a consequence of under-specification rather than disciplined editing.

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 input schema is fully documented. However, for a 10-parameter search tool with no annotations, the description supplies no filter-combination semantics or routing guidance, leaving the agent to guess at invocation 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?

Schema description coverage is 100% — all 10 parameters carry their own descriptions, including formats and defaults. The description adds no parameter-level meaning beyond that, so the baseline of 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 generic verb+resource ('Search for emails') but the qualifier 'matching specific criteria' is filler that adds no discriminating information. It does not distinguish this tool from the sibling list_emails, which an agent would need to know about to pick correctly.

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, no mention of when search is preferable to list_emails, and no note about how filters combine (AND semantics) or what happens with all-null criteria. The agent must infer the entire usage model.

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 disclose that sending is irreversible, what account/permission is required, whether delivery failure is reported, or any rate limits – critical for an outbound-message tool.

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 wasted words and the action front-loaded. It is efficient, though its brevity is partly a symptom of thin coverage rather than disciplined editing.

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. However, for a mutating, irreversible tool with no annotations and rich sibling tooling (reply, forward), the description omits usage routing, side-effect disclosure, and auth expectations – too thin for this complexity.

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 100%, so every one of the 8 parameters (to, cc, bcc, subject, body_text, body_html, reply_to, attachments) is already documented in the schema. The description adds nothing beyond that, which is the correct baseline of 3.

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 (send) and resource (new email) plus the account context (METU Webmail). The word 'new' implicitly separates it from reply_email and forward_email, but the description never names those siblings, so the distinction is left to inference.

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 'new email' – an agent can guess this is for composing rather than replying or forwarding, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many sibling mail tools.

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