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

The description explicitly lists returned fields (title, cwd, status, todos, message count) which goes beyond the readOnlyHint annotation. It also states 'Read-only,' consistent with annotations. No contradiction or missing behavioral detail like error cases, but for a simple read operation this is sufficient.

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 with no fluff. The main purpose is front-loaded, followed immediately by the usage prerequisite. Every word earns its place; it is concise while packed with necessary 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?

For a read-only tool with 2 parameters, no output schema, and no nested objects, the description covers the returned data, the source of parameters, and the read-only nature. Nothing critical is missing for an agent to call it 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 descriptions for both agent and session_id. The description adds value by clarifying that these come from list_sessions/search_sessions results, giving origin context that helps the agent know exactly what values to pass.

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 a specific action: 'Get a single session's title, cwd, status, todos, and message count.' This differentiates it from sibling tools like list_sessions (listing) and get_transcript (transcript). It also specifies the exact data returned.

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 provides a direct prerequisite: 'Use the agent and id fields from a list_sessions/search_sessions result.' This implies a workflow but does not explicitly mention when not to use alternatives like get_transcript. Still, it gives clear context on how to obtain the required parameters.

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 description adds substantial behavioral context beyond the readOnlyHint annotation: secrets are redacted by default and only exposed when raw is set; results are paginated with most recent messages first; and it repeats 'Read-only' for emphasis. The raw parameter's trust caveat is also surfaced. These are meaningful disclosures that help the agent predict side effects and data handling.

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 three short sentences with zero filler. The core action is front-loaded, followed by the critical redaction detail and then the input-source note. Every sentence earns its place and the structure is ideal for quick scanning.

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 has six parameters, pagination, and role filtering, but no output schema. The description covers the essentials—purpose, default ordering, redaction behavior, and input provenance. It does not explicitly describe the response structure (e.g., list of messages with roles/content), but for a transcript fetch this is inferable. A minor gap regarding error conditions or rate limits exists, but overall it is sufficiently 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 the schema already documents all parameters (e.g., raw, limit, cursor, session_id). The description adds only a slight reminder to source agent and id from list/search, but that is largely redundant with the schema's session_id description. No new parameter meaning is introduced, so the 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 specific verb (fetch) and resource (a session's transcript), and immediately adds pagination and default ordering. It distinguishes itself from siblings by focusing on transcript content, not session metadata or searching. The phrase 'Use the agent and id fields from a list_sessions/search_sessions result' also implies this tool is downstream of those, further clarifying its role.

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 instructs the agent to obtain agent and session_id from list_sessions/search_sessions, which is a clear prerequisite. However, it does not explicitly state when to prefer this tool over get_session or search_sessions, nor does it give an exclusion condition. The guidance is implied by the resource type, but not as explicit as the best examples.

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 annotation readOnlyHint=true already discloses the read-only nature, and the description redundantly states 'Read-only.' The description adds a bit of behavioral context by describing the output fields (running, topic, status), but it does not disclose potential limitations like pagination, error behavior, or rate limits. Since the annotation covers the safety profile, the description adds minimal extra 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?

The description is a single, well-structured sentence that front-loads the verb and resource, then provides the scope and return info. There is no redundancy or filler—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?

With no output schema, the description compensates by stating what fields are returned (running, topic, status), which is helpful. It does not explicitly mention pagination or limit behavior, but the schema already defines 'limit' as 'Max sessions to return, per adapter.' The description is adequately complete for a listing operation.

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 description coverage is 100%, so all 4 parameters (cwd, agent, limit, running_only) are already well-documented in the schema. The tool description does not add any semantic meaning beyond what the schema provides, so it meets the baseline of 3 without further contribution.

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 ('List'), a precise resource ('coding-agent sessions on this machine'), and enumerates the agent types (Claude Code, OpenCode, Cursor, Codex). It also clarifies what is returned ('what's running, its topic, and its status'), which distinguishes it from sibling tools like get_session that fetch a single session. This is clear and specific.

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 (e.g., use this to get a broad overview of sessions on this machine) but does not explicitly state when to prefer this over search_sessions or get_session. There is no mention of alternatives or when not to use it, leaving some inference to the agent.

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 set readOnlyHint=true, and the description reinforces this by stating 'Read-only'. It adds value by mentioning 'case-insensitive' and the dual search targets (titles and recent transcript content), which are non-obvious behaviors not captured in the schema or annotations. No contradiction.

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 one sentences with no fluff, front-loading the main purpose. It includes 'Read-only' and 'case-insensitive' efficiently. The only minor issue is the parenthetical 'and recent transcript content' could be clearer, but it does not waste 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?

The tool is simple enough that the description mostly suffices, but it lacks parameter semantic details that are critical due to 0% schema coverage. An agent might misuse the 'agent' filtering or misunderstand 'limit' behavior. Without output schema, the return format is also undocumented, but that is less critical for a search tool. On balance, it falls short of full 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?

With 0% schema description coverage, the description must explain parameters, but it does not. It omits meaning for 'agent' (which has an enum), 'limit', and 'query'. The description only hints at search functionality but provides no detail on how these parameters affect behavior, such as the default agent scope or limit interpretation. This is a significant gap given the low coverage.

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 explicitly states 'Search session titles (and recent transcript content) for a substring', combining a specific verb with clear resources. It also distinguishes itself by mentioning read-only and case-insensitive behavior, setting it apart from siblings like list_sessions or get_session.

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 (searching across sessions) but does not explicitly compare to siblings. It lacks guidance on when not to use this tool, such as when full transcript retrieval is needed (get_transcript) or when listing all sessions without search is desired (list_sessions). However, the search scope is clear enough for an agent to infer common use cases.

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