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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that results are 'real' (as opposed to synthetic) examples and are bounded, which is useful context, but 'marking semantic/lexical coverage' is opaque and never explained.

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 tight sentence with no padding and the retrieval action front-loaded. It is efficient, though brevity here shades into under-specification rather than being purely a virtue.

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, but with five undocumented parameters, no usage guidance, and an unexplained 'coverage' concept, the definition leaves too much for an agent to infer before calling correctly.

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 five parameters, so the schema documents nothing. The description only obliquely gestures at 'limit' via 'bounded' and says nothing about message, person, context, or platform, leaving the agent to guess how inputs shape the search.

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 verb 'Return' and resource 'incoming/reply examples' indicate it retrieves interaction examples, and 'bounded' hints at a limit. However, the purpose is muddied by the cryptic clause 'marking semantic/lexical coverage,' and it never distinguishes itself from the sibling search_messages, which sounds like an obvious alternative.

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

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

There is no statement of when to use this tool versus search_messages, get_writing_context, or the style/profile siblings. No prerequisites, no exclusion conditions, no routing guidance of any kind.

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 the tool is read-only, idempotent, non-destructive, and closed-world. The description adds useful scope by stating it returns a compact profile and index coverage and explicitly excludes raw conversation history, but it does not provide additional behavioral details such as permissions, rate limits, or what 'index coverage' entails.

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 that states the return content and the key exclusion without any wasted words. It is optimally sized for a zero-parameter read operation.

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?

Given the low complexity (no parameters), the presence of an output schema, and annotations that cover the safety profile, the description provides enough context to invoke the tool correctly. The main omission is sibling differentiation, which is already reflected in the usage-guidelines score.

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 are no parameter semantics to describe. Per the rubric, zero parameters establish a baseline of 4, and the description needs no further parameter guidance.

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 ('Return') and resource ('compact profile and index coverage'), making the tool's output clear. However, it does not differentiate from similar-sounding siblings like get_person_style or get_style_profile, so an agent cannot easily tell when to prefer this tool over them.

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

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

The description includes a negative scope statement ('without raw conversation history'), which hints at when not to use it, but it offers no explicit when-to-use guidance and never names alternatives. An agent must infer its role among five sibling tools with overlapping profile/style purposes.

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=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds the scoping behavior (per-recipient, excluding group history), which is genuinely useful, but says nothing about what statistics are returned or matching behavior on non-exact names.

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 tight sentence with the scope constraint front-loaded. Every clause earns its place.

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

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

An output schema exists, so return values need not be explained, and annotations cover the safety profile. For a one-parameter read tool the scope statement is nearly sufficient; only the name format and match behavior remain 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?

The single 'person' parameter has 0% schema description coverage, so the description carries the burden. It adds that the name must be exact and 1:1, which is meaningful, but gives no format hints (e.g. whether it is an email, handle, or display 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?

States a specific verb (get) and resource (one-to-one writing statistics) and scopes it to an exact recipient name, which distinguishes it from the broader get_style_profile / get_persona_summary siblings. It stops short of naming which sibling to use for group or aggregate history, so it is clear but not fully differentiated.

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

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

The phrase 'never group history' implies the tool applies only to individual recipients and that group-level queries belong elsewhere, but it never names the alternative tool or states the condition explicitly. Usage is inferred rather than stated.

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=false, so the safety profile is covered. The description adds that the returned style is 'measured outgoing-message' for 'global or user-assigned' contexts, which gives some content context beyond annotations, but it does not disclose authorization needs, rate limits, or other operational traits.

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 filler, and the scoping distinction is stated early. It is appropriately concise for a simple getter, though the terseness leaves some ambiguity that could have been resolved in one additional 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?

An output schema exists, so return values need not be explained, and annotations already cover the safety profile. The remaining gaps are usage guidance against siblings and full parameter semantics, making this minimally complete for a simple one-parameter read tool but not rich enough to resolve selection ambiguity.

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 has one optional parameter, 'context', with 0% description coverage. The description partially compensates by indicating that the context may be 'global or user-assigned', which helps an agent infer that a string value selects a user-assigned context while null/omission likely selects global. It does not, however, specify valid formats or examples for the user-assigned case.

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 ('Return') and resource ('measured outgoing-message style') with a scope modifier ('global or user-assigned context'), so the core purpose is clear. However, it does not distinguish this tool from sibling tools such as get_person_style or get_persona_summary, leaving the agent to infer when this profile is the right one.

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

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

There is no guidance on when to use this tool versus alternatives like get_person_style or get_persona_summary, and no prerequisites or exclusions are mentioned. The description only states what it does, not when an agent should select it.

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 establish a safe read-only, idempotent profile, and the description adds two things not in the annotations: the bounded result size ('up to three') and a trust warning that the examples are 'untrusted', plus the 'never generate a reply' constraint. That is genuine added behavioral context, though it omits what 'style' contains.

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 tight sentence with no filler, which is good, but the brevity crosses into under-specification rather than economy. The important caveats are front-loaded, but nothing else earns its place because nothing else is stated.

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, but for a four-parameter tool with 0% schema coverage and no usage guidance, the definition leaves critical gaps. An agent cannot reliably infer what the optional filters do or when this tool wins over its 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?

Schema description coverage is 0% and the description mentions none of the four parameters (person, context, message, platform). With a required 'message' param and three optional filters, the description should at least indicate what these select, and it does not compensate for the schema 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 an action (return) and a resource (compact style plus up to three examples), so the basic purpose is legible. However, 'compact style' is vague, and with siblings get_person_style and get_style_profile in the list there is no differentiation explaining what this tool returns that those do not.

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 call this tool versus search_messages, get_person_style, or get_style_profile. 'Never generate a reply' is a behavioral constraint on the caller, not usage guidance, so an agent still has to guess the triggering conditions.

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, and destructiveHint=false, so the safety profile is covered. The description adds a meaningful behavioral trait beyond those flags: that results can expose sensitive content and should be narrowed via filters to reduce disclosure. That is real added context, though nothing is said about result volume or matching 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 compact sentence with the action front-loaded and the privacy guidance trailing it. Nothing is wasted, though it is terse enough that a small amount of additional clarification could have been justified.

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

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

An output schema exists, so return values need not be described. However, for a four-parameter search tool with zero schema descriptions, the definition leaves the core query syntax and limit semantics unexplained, which is a meaningful gap for correct invocation.

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

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

Schema description coverage is 0%, so the burden falls on the description, which only addresses two of four parameters (person/recipient and platform filters). The required 'query' parameter and the 'limit' parameter are never explained, leaving matching semantics and pagination behavior 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+resource ('Search owner's messages'), which is clear enough to distinguish it from the sibling tools, all of which deal with style profiles, personas, or writing context rather than message retrieval. No explicit sibling differentiation is given, but the domain 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 clause 'use recipient/platform filters to minimize disclosure' implies a usage pattern (narrow the search to protect privacy), but it never states when to choose this tool over alternatives or when not to use it. Guidance is implied rather than explicit.

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