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. It does not state that this is a read-only, non-destructive enumeration, nor mention ordering, pagination, or behavior on emails with no parts, for a tool that the agent must be able to call safely.

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 enumerating verb front-loaded and no filler. It is appropriately sized, though the parenthesis adds clarification at the cost of a slightly denser read.

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 presence of an output schema means return values needn't be explained, which offsets some gaps. However, with no annotations and an undocumented required path parameter, the definition is only minimally sufficient for a read tool with ambiguous input.

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% and the single parameter "path" is undocumented in both schema and description. "Of one email" hints that path identifies the email, but the format (filesystem path, ID, URI) is left ambiguous, which is a real risk for a required parameter.

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) and resource (MIME parts: attachments, inline images, bodies) of a single email, and parenthetically disambiguates what a "MIME part" is. It does not distinguish the tool from siblings like open_attachment or view_emails, 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives (e.g., open_attachment to fetch the actual content). Usage is only weakly implied by "of one email," so the agent must infer both trigger conditions and relationships to siblings.

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 implies a read-only documentation lookup, but never states that explicitly, nor does it describe output size or whether topics can be combined. For a low-risk help tool this is adequate, but it adds little behavioral context beyond the topic list.

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 purpose and the routing condition, followed by a compact topic legend. No filler.

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

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

An output schema exists, so return values need no explanation. For a single-enum documentation tool, the purpose, trigger condition, and value semantics are all 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% and the single parameter is an enum, so the description must supply meaning for the values. It does: each of query, fields, find, and extract is annotated with a parenthetical scope, letting the agent pick the right topic without guessing.

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 resource ('full mu reference') and enumerates the four topic areas it covers, so an agent knows exactly what it gets. It also distinguishes itself from search_emails by positioning itself as the deeper version of that tool's short guide.

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

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

Gives an explicit trigger condition ('when the short guide in search_emails isn't enough') and names the alternative, so the agent can decide between calling search_emails' inline guide and calling this tool. The inverse condition (short guide suffices) follows directly.

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 files land in a temp dir and that open_in_viewer launches the OS default application (a real side effect), but it says nothing about overwrite behavior in the temp dir, permissions, or what happens when no attachment matches.

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?

Front-loaded with the core action, followed by a useful return-value note and a clean Args block. Slightly more verbose than strictly necessary, but every line adds information and nothing is repeated.

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-value detail is not required, and the description still notes that file paths come back. All three parameters are explained despite 0% schema coverage. Only the lack of sibling routing and failure-mode context keeps it from a 5.

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 does: path is identified as a message file path, pattern is described as case-sensitive PCRE matched against attachment names with concrete examples and its default, and open_in_viewer is explained as opening each file with the OS default app.

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: save an email's attachments to a temp dir, with optional opening. It is clearly distinct from list_attachments in intent (save/dump vs. list), although it 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?

Usage is implied rather than stated: 'Returns the saved file paths, so their contents can be read afterwards' hints at the workflow (save, then read). There is no explicit when-to-use/when-not guidance and no pointer to list_attachments or view_emails for the cases where saving is unnecessary.

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 key behavior: the exact one-line-per-message return format, the fact that max_results truncation is possible and how to react ('raise it or narrow the query if the result is cut off'), and the semantics of newest_first ('newest/Z first'). It never explicitly states read-only/no-side-effect behavior, but search semantics imply it.

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?

Long but dense: purpose and return format are front-loaded, then the query grammar is organized under tight bullet headings with examples. Every block is load-bearing for a tool whose parameter is a mini-language; nothing reads as filler.

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

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

An output schema exists, yet the description still front-loads the return line format, and all five parameters, the query grammar, and the follow-up tools are covered. For a search tool of this complexity, an agent has everything needed to construct a correct call.

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

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

Schema description coverage is 0%, so the description must compensate, and it documents all five parameters: query (with a full grammar and examples), max_results (a cap plus the truncation remedy), sort (field to sort by), newest_first (reverse order), and include_thread (also return other messages from matching threads). This is meaningfully more than the bare schema types/defaults.

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 ('Search the local mail index with a `mu` query') and immediately clarifies the exact return shape (`date | from | subject | path`). It also names the sibling tools that consume the output (view_emails, list_attachments), so an agent can place it in the workflow 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?

Gives extensive guidance on how to use it (full query grammar, field list, date units, flag list, operators, five concrete examples) and how to chain it to siblings via the returned path. It does not explicitly state when to prefer it over mu_help or when a narrower query is required beyond the truncation note, so it stops short of a full when/when-not statement.

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 add real value by disclosing the HTML-to-plain-text conversion and the per-message truncation cap, but it is silent on error behavior for invalid paths, whether truncation is signaled to the caller, and whether attachments are included. Useful but incomplete for an annotation-free 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?

Four short lines, front-loaded with purpose and the routing cue before the Args block. Every sentence earns its place with no filler.

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

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

An output schema exists, so return-value documentation is not required, and the description covers purpose, input provenance, format conversion, and truncation policy. It is nearly complete for a simple two-parameter read tool; only error/edge-case behavior is unaddressed.

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 define both parameters, and it does: 'paths' as message file paths and 'max_chars' as a per-message cap on returned text. The definitions are accurate but terse, and it doesn't explain what happens when the cap is hit (truncation semantics), which is the one behavior an agent would most want clarified.

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 ('Read emails') and specifies exactly what is returned (headers + body as text). It also anchors the input to the sibling search_emails, so an agent can distinguish it from search_emails, list_attachments and open_attachment 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?

It explicitly tells the agent where the required 'paths' come from ('given paths from search_emails'), which is the key usage constraint. It does not state when NOT to use it or point to list_attachments/open_attachment for attachment content, so it stops short of full when/when-not guidance.

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