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

Explicitly declares 'Read-only with no side effects.' Since no annotations are provided, the description adequately covers behavioral transparency. However, it lacks details on sorting or time window for 'recent activity,' which would be beneficial.

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, each serving a purpose: first conveys functionality, second declares safety, third provides usage guidance. No wasted words.

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 one parameter and an output schema, the description covers purpose, behavior, and usage guidance comprehensively. No gaps remain for this complexity level.

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?

Only one parameter (limit) with 100% schema description coverage. The tool description adds no extra meaning beyond the schema's explanation of the limit range and default. Baseline score 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?

Clearly states the tool lists Signal chats ranked by recent activity with specific fields (last message date, last reply date, count of unanswered inbound messages). Differentiates from sibling list_chats by specifying its unique output.

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 states when to use this tool ('identify chats that need a response') and when to use the alternative ('Use list_chats instead for a general chat directory with message previews').

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 provided, so description bears full burden. Discloses that it is read-only on Signal data and writes a decrypted copy to a temporary directory. Adds important safety and side-effect information beyond basic decryption.

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 covering purpose, parameter source, and usage context. No redundancy, well-structured, and front-loaded with the core action.

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 moderate complexity (2 parameters, output schema exists), the description covers purpose, parameter sourcing, safety behavior, and usage timing. No obvious gaps for an agent to correctly select and invoke the 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 coverage is 100% with detailed descriptions. Description adds context on the origin and nature of the parameters (from attachment metadata, base64-encoded key structure), which aids correct invocation beyond schema alone.

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?

Clearly states verb ('Decrypt'), resource ('locally stored Signal attachment'), and outcome ('return the path to the decrypted file'). Distinct from siblings which involve chat activity, status, lists, and 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?

Explicitly states where the input parameters come from ('encrypted_path and local_key values come from attachment metadata in read_messages or search_messages') and advises using it after reading messages with attachments. No explicit exclusions, but 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?

No annotations, but description states 'Read-only with no side effects' and lists return fields, fully disclosing 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?

Two sentences, front-loaded with purpose, no wasted words. Efficient and clear.

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?

Tool is simple with no parameters. Description covers purpose, return fields, and usage context. Output schema exists for further detail, making this 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?

No parameters; schema coverage 100%. Description adds value by explaining return fields, which is sufficient for a zero-parameter tool.

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?

Description clearly states the tool checks server ability to read and send messages, with specific verb and resource. Distinct from sibling tools like read_messages or send_message.

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 recommends calling before read or send operations, providing clear context. No need for alternatives as this is a single-purpose health check.

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?

Declares read-only with no side effects, and mentions data source and sorting. Without annotations, this provides sufficient behavioral context.

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 efficient sentences: purpose, output details, and usage guidelines. No unnecessary words.

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 2 simple parameters with full schema, no annotations, and an output schema present, the description fully covers what the agent needs: purpose, output format, and when 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% with detailed parameter descriptions. The description adds no extra meaning beyond the schema, so 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?

Clearly states it lists direct and group Signal chats from local desktop database, sorted by most recent message. Differentiates from list_groups by specifying when to use each.

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 advises to use this tool to discover chat names before calling read_messages or search_messages, and to use list_groups for group_id values needed for send_message.

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 declares 'Read-only with no side effects' and explains the fallback from signal-cli to local desktop database (noting that group_id is missing in fallback). This is good but could be improved by mentioning any rate limits or error conditions.

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, each serving a distinct purpose: purpose and output fields, safety and fallback, usage guidance and sibling differentiation. No wasted words, and critical information is front-loaded.

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 all essential aspects: purpose, output fields, sorting, read-only safety, fallback behavior, when to use, and alternative tools. With an output schema available, return values are handled by schema. No gaps identified.

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?

Input schema has 100% description coverage and describes both parameters well. The description adds value by stating the output is sorted alphabetically, which is not in the schema. Baseline is 3; the sorting detail justifies a 4.

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?

Clearly states the verb ('List'), resource ('Signal groups'), and the specific fields returned (group_id, name, description, members, admin lists). Also distinguishes from sibling 'list_chats' by noting that list_chats provides a combined view of direct and group chats.

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 states when to use this tool: 'to obtain group_id values needed by send_message'. Also provides an alternative for a different use case: 'Use list_chats instead for a combined view'. Additionally, describes fallback behavior, giving clear context on data availability.

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?

States 'Read-only with no side effects', and describes what each message includes. No annotations provided, so description carries full burden; it adequately discloses read-only nature and output detail.

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 concise sentences with no wasted words. Front-loads purpose and immediately gives key details.

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 5 parameters with full schema coverage and output schema present, the description covers purpose, output format, prerequisite, and alternative tool sufficiently without needing to repeat schema details.

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 adds minimal extra meaning beyond the schema (e.g., chat_name must be exact from list_chats), but does not significantly enhance parameter understanding.

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?

Description clearly states 'Read messages from a single Signal chat' with verb and resource, and distinguishes from sibling 'search_messages' which finds messages by keyword across chats.

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?

Provides prerequisite ('Requires an exact chat name from list_chats') and an alternative ('Use search_messages instead'), but does not explicitly exclude other inappropriate use cases.

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?

Declares 'Read-only with no side effects', which covers safety. No annotations exist, so description carries full burden. Could mention search scope (message bodies only) but 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?

Two sentences only, no wasted words. Front-loaded with purpose and scope.

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 output schema exists, description is comprehensive: covers usage scope, safety, sorting, and links to alternative. Only minor omission is pagination details, but acceptable.

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 baseline is 3. Description adds value by explaining scope ('within one chat or across all chats') and sort order ('newest-first'), enhancing what schema provides.

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?

Clearly states the tool searches message bodies by keyword, within one chat or all, and returns newest-first. Distinguishes from sibling read_messages by specifying its use for content search versus chronological browsing.

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 tells when to use ('to find messages by content') and when not to ('use read_messages instead to browse a specific chat chronologically'), with a direct sibling alternative.

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 present, so the description fully disclosures behavioral traits: it is a write operation, rate-limited (1/s per recipient, 10/60s globally), requires signal-cli and SIGNAL_ACCOUNT, and hints at the return structure. This covers all necessary behavioral context.

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 concise, with the main purpose front-loaded, followed by essential rules and constraints in a logical order. Every sentence adds value, and there is no redundant or extraneous content.

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 (4 params, 1 required, mutual exclusivity, rate limits, prerequisites, and output schema), the description covers all necessary aspects: how to specify recipient, error conditions, rate limits, preconditions, and return format. It is fully sufficient for correct agent usage.

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%, and each parameter has a clear description in the schema (including mutual exclusivity). The tool description restates the exclusivity rule but adds no new semantic details about the parameters themselves beyond what the schema already provides.

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 begins with 'Send a text message via Signal to a direct recipient or group,' which clearly identifies the action and resource. It further distinguishes itself from sibling tools (e.g., read_messages, get_status) by stating it is a write operation that delivers a real message.

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 explicit when-to-use guidance: exactly one recipient field must be supplied, and it warns against providing zero or multiple. It also specifies prerequisites (call get_status first) and rate limits, giving clear boundaries for safe invocation.

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