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

With no annotations provided, the description carries full burden. It explicitly states the action is recoverable and not permanent deletion, which is a key behavioral trait. It does not cover permissions, idempotency, or effects on existing state, but for a simple move operation this is adequate.

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 two sentences long, immediately states the action, and adds the critical recoverability information. No unnecessary words. Perfectly front-loaded and concise.

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 simplicity of the operation (move to trash with one parameter), the description is mostly complete. It lacks details on return values or error cases, but no output schema exists. A note about idempotency or what happens if mail already in trash would improve completeness.

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 single parameter 'id' is described in the schema as 'Identifiant du mail'. The description adds no additional meaning beyond what the schema provides, so 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 clearly states the action ('Déplace un mail vers la Corbeille') and the resource ('mail'). It adds specificity by noting the action is recoverable, distinguishing it from permanent deletion. However, it does not explicitly differentiate from sibling tools like 'deplacer_mail' which moves to other folders.

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 implies use cases by emphasizing recoverability, suggesting it should be used when deletion should be reversible. It does not explicitly state when not to use it or mention alternatives beyond implying contrast with definitive deletion.

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 burden. It discloses basic behavior: draft created (not sent), appears in drafts folder, multiple recipients allowed. However, it misses details like authentication needs, error handling, or return value.

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 sentences with no wasted words. The first sentence front-loads the core purpose. Every sentence adds essential 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?

Given 6 parameters, no output schema, and no annotations, the description explains the core function (draft creation) and location. But it lacks detail on return values or error cases, leaving some gaps for a creation tool.

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 descriptions cover 100% of parameters. The description adds minimal extra meaning beyond the schema, such as clarifying multiple recipients with commas, but this is already in the schema. Baseline score of 3 is 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?

The description clearly states 'Crée un brouillon dans Mail SANS l'envoyer', specifying a specific verb and resource. It distinguishes from siblings like 'envoyer_mail' by emphasizing 'SANS l'envoyer'.

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 provides clear context: use this tool to create a draft without sending. It implies when to use but does not explicitly exclude other scenarios or list alternatives like 'repondre_mail'.

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 carries full burden. It discloses the action is reversible, which is a key behavioral trait. However, it does not mention what happens if the folder doesn’t exist, permissions needed, or other side effects, making it moderately transparent.

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 two concise sentences with zero wasted words. The key action and constraint are front-loaded, making it easy to parse.

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 description covers the basic move operation and reversibility, but it does not differentiate from the sibling corbeille_mail (trash) nor explain what constitutes a valid folder or error behavior. Given the simple tool, it is marginally adequate but could be more 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 coverage is 100% (both parameters have descriptions). The description adds no new semantic info beyond emphasizing exact folder name, which is already in the schema. Baseline 3 is 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?

The description clearly states 'Déplace un mail vers un dossier' (verb + resource) and specifies the exact folder name requirement, distinguishing it from sibling tools like corbeille_mail (which likely moves to trash). 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?

The description provides guidance on usage by stating the folder name must be exact as it appears in Mail, and notes the action is reversible. However, it does not explicitly contrast with sibling tools or state when to avoid using this tool.

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?

Even without annotations, the description transparently discloses the irreversible, immediate nature of the action: 'action sortante et définitive : le mail part'. This fully informs the agent of the tool's side effect.

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?

Concise two-sentence description with front-loaded key action ('ENVOIE immédiatement') and no unnecessary words. Each sentence serves a purpose: action, usage guidance, and parameter hint.

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 send-email tool with no output schema and well-covered parameters, the description is complete. It covers irrevocability, alternative for draft, multi-recipients, and account requirement for sender. No critical 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?

Schema coverage is 100%, but the description adds value by noting that 'expediteur' must correspond to an account, referencing a related tool 'lister_comptes'. Other parameters are adequately described in the schema, and the description reinforces the comma-separated list for recipients.

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 clearly states the tool sends an email immediately, using strong verbs 'ENVOIE immédiatement' and differentiating from the sibling 'creer_brouillon' which prepares a draft. 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?

Explicitly instructs to use only when the user truly wants to send, and provides a direct alternative ('creer_brouillon') for previewing. Also notes that multiple recipients are allowed, separated by commas.

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. It states that the tool returns full email content but does not disclose whether reading the email changes any state (e.g., marking as read) or any other side effects. This is a non-negligible gap for a read operation, but the core behavior is clear.

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, efficient sentence that front-loads the tool's action and includes all essential information: what it does, what fields it returns, and how to obtain the input. There is no waste or redundant text.

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 tool's simplicity (single parameter, no output schema, no nested objects), the description adequately covers the purpose, input source, and returned fields. It lacks error scenarios or output format details, but the complexity is low, so the description is sufficiently complete for an agent to use the tool 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 coverage is 100% with a description for the 'id' parameter. The tool description adds value beyond the schema by explaining that the id is obtained from lister_mails or rechercher_mails, guiding the agent on how to acquire a valid input.

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 specific verbs ('Renvoie') and clearly states the resource ('contenu complet d'un mail') and the fields returned (sender, subject, date, status, body). It distinguishes the tool from siblings like lister_mails and rechercher_mails by specifying that it returns full content from an ID obtained via those tools.

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 explicitly tells the agent that the input ID should come from lister_mails or rechercher_mails, providing clear usage context. It does not include explicit when-not-to-use statements, but the sibling tool names (e.g., envoyer_mail, deplacer_mail) imply alternatives for other actions.

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 bears full burden. It accurately describes the output (name and email addresses) and implies read-only behavior. No side effects or contradictions are present.

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 main action, no redundant information. Every sentence 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 listing tool with no output schema, the description is complete: it specifies what is listed (accounts) and what details (name and email). No 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 input schema has no parameters, so it provides no meaning. The description adds value by explaining the output and its purpose, compensating for the empty 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 clearly states the tool lists connected email accounts with name and email addresses, using a specific verb ('liste') and resource ('comptes'). It distinguishes from sibling email tools (e.g., lister_mails, envoyer_mail) by focusing on accounts rather than 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 description explicitly says it is useful for knowing which address to use before creating a draft or sending an email, providing clear use context. It does not specify exclusions, but for a simple listing tool, this is sufficient.

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. The description mentions it lists latest emails from all combined inboxes and returns IDs for reuse, but does not disclose ordering, rate limits, authentication needs, or any other behavioral traits beyond basic read operation.

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 two sentences, front-loaded with the main purpose. It is concise and covers key points without unnecessary detail, though the second sentence could be slightly more streamlined.

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 (3 optional parameters, no output schema), the description adequately specifies return fields and the reuse of identifiers with other tools. However, it lacks details on ordering and pagination, which slightly reduces completeness.

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 baseline is 3. The description repeats parameter info (filter by unread/sender, limit) without adding new meaning beyond what the schema already provides in parameter descriptions.

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 clearly states the tool lists latest inbox emails with filtering options and specifies return fields (ID, sender, subject, date, status). It distinguishes itself from siblings like 'rechercher_mails' by focusing on browsing recent emails rather than full-text search.

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 implies use for browsing latest emails and filtering by unread/sender, but does not explicitly state when to use this tool vs alternatives like 'rechercher_mails' or provide exclusions. No when-not guidance is given.

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 full burden. It discloses the core behavior (toggle read/unread) but omits any side effects, permissions, or idempotency details. For a simple toggle, this is acceptable but not exemplary.

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, concise sentence that efficiently conveys the tool's purpose without unnecessary detail. Every word 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?

Given the low complexity of the tool and the absence of an output schema, the description is adequate. However, it does not specify the return value or confirm success/failure behavior, which would enhance completeness.

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 input schema already defines both parameters ('id' as mail identifier, 'lu' as boolean flag). The description adds no additional meaning beyond what the schema provides, so a baseline score of 3 is 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?

The description clearly states the tool's action: marking an email as read or unread using its identifier. It uses a specific verb+resource combination and distinguishes the tool from siblings like 'lire_mail' (reading) and 'corbeille_mail' (trashing).

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 provides no guidance on when to use this tool versus alternatives (e.g., moving, deleting, or sending). There is no mention of prerequisites or exclusion criteria, leaving the agent without context for selection.

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 full burden. It discloses the scope (400 most recent), search fields (subject, sender, body optionally), and performance consideration (slower with body). Missing details on result format or sorting, but sufficient for a search 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?

Two concise sentences, front-loaded with core purpose. Every sentence adds value: scope, search targets, conditional body search, optional filters. No redundancy.

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 no output schema and no annotations, the description covers core behavior and all parameters. It could mention what the results contain (e.g., subject, sender, date), but for a search tool, the description is sufficiently complete for an agent to use.

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%, but the description adds meaning: 'mot_cle' is searched in subject/sender, 'expediteur' is a substring filter, 'depuis_jours' filters by recency, 'inclure_corps' makes it slower. This goes beyond schema definitions.

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 clearly states it searches recent inbox emails by keyword in subject and sender, with optional body search and filters. This distinguishes it from sibling tools like 'lister_mails' which lists all mails without search.

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 explains when to use: to search emails by keyword with optional filters. It does not explicitly state when not to use or provide alternatives, but the context is clear.

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 transparency burden. It discloses key behaviors: default draft creation (envoyer=false), inclusion of original thread/recipient/subject, and the effect of repondre_a_tous. It does not mention return values, error handling, or authorization needs, but covers the primary behavioral traits well.

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 extremely concise with two front-loaded sentences. The first sentence states the core function, and the second clarifies the default behavior and the a_tous option. No unnecessary words, making it easy to parse quickly.

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 tool's complexity (7 parameters, no output schema) and 100% schema coverage, the description is reasonably complete. It covers the main use case, default behavior, and the optional a_tous. It lacks explicit mention of return values or error conditions, but for a reply tool this is 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 coverage is 100%, so the description adds limited value over the schema. It echoes the repondre_a_tous parameter's effect and the envoyer default, but does not provide additional semantic meaning beyond what the schema already explains. Baseline 3 is 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?

The description clearly states the tool's purpose: replying to an email by its ID, with specific behaviors like copying the thread, recipient, and subject with 'Re:'. It distinguishes itself from sibling tools like creer_brouillon (creating a fresh draft) or transferer_mail (forwarding), as it explicitly handles replying.

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 implies usage for replying to an existing email, mentioning the default draft creation and the option to send directly. However, it does not explicitly state when to use this tool versus alternatives like creer_brouillon or envoyer_mail, nor does it mention prerequisites or constraints.

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?

Without annotations, the description fully discloses that the tool is non-destructive ('sans toucher aux messages' – touches no messages) and confirms it is a safe access check. This gives complete behavioral transparency.

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 concise sentences with no waste. The first sentence states purpose and key safety property; the second provides usage guidance and output interpretation. Every sentence 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 simple test tool with no parameters and no output schema, the description is complete: it explains purpose, behavior, result interpretation, and context within the sibling set.

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?

No parameters exist, so description adds no param info beyond schema. Baseline of 4 is appropriate given 100% schema coverage and zero parameters; the description provides context for the tool's function.

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 clearly states the tool tests whether Claude can control the Mail app, emphasizing no message interaction. This distinguishes it from sibling tools that perform actual mail operations.

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 indicates use in case of problems and explains how to interpret the response (success means access OK, error indicates next steps). It does not explicitly list when to avoid using it or alternative tools, but the context is clear.

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 full burden. It discloses draft-by-default, sending behavior, and that it adds header/content. Side effects are minimal and implied.

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, no filler. Front-loaded with verb and object: 'Transfère un mail...'. Every sentence 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 tool with 7 parameters (2 required) and no output schema, the description provides essential behavior and parameter context. Could mention result/return but not critical.

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 covers all 7 parameters with descriptions. The description adds value by noting default for 'envoyer' and optional 'expediteur', going beyond 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 clearly states the tool transfers a mail to recipients, adding headers and original content. It distinguishes from siblings like 'repondre_mail' (reply) and 'envoyer_mail' (send).

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 explains default draft behavior and the optional 'envoyer' parameter to send directly. It references 'lister_comptes' for sender but doesn't explicitly differentiate from siblings in when to use.

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