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

Annotations already declare destructiveHint=true, so the destructive nature is covered structurally. The description adds a useful nuance—that calling it on an idle session is safe—which goes beyond the annotation. However, it does not disclose whether aborting is irreversible, whether a running computation is killed, or what happens to partial results.

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, no filler, and the core action is stated first. The safety note is useful and 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 one-parameter destructive action with no output schema, the description is nearly complete: it states purpose and a safe-call condition. It could be slightly richer by explaining the post-abort state of the session, but an agent can invoke this tool correctly with what is provided.

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 session_id is already fully documented as the session id returned by create_session. The tool description adds no further parameter guidance, so the baseline score of 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 uses a specific verb ('Stop') with a clear resource ('a long-running or unwanted delegated task'), and the title names the action and object. It is immediately distinguishable from siblings like create_session and 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 gives clear signals about when to use it: for long-running or unwanted delegated tasks. It also provides a useful safety condition ('Safe to call when the session is already idle'). It does not explicitly name alternatives or describe when not to use it, but the context is sufficient for most selection decisions.

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 supply only openWorldHint=true, so safety/lifecycle behavior is mostly unspecified. 'Persistent' and 'keep the agent's context between calls' disclose server-side state retention, which is real added value, but nothing is said about session lifetime, default permissions, or the effect of the allow_bash/allow_edits grants.

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, zero filler. The purpose is front-loaded and the follow-up instruction is packed into the second sentence without 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?

For a six-parameter session-creation tool with thin annotations and no output schema, the description omits what the call returns (a session identifier presumably needed for send_message) and says nothing about permissions defaults. Purpose and next step are covered, but the agent lacks enough to use the result confidently.

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 all six parameters (cwd, agent, model, title, allow_bash, allow_edits) are already documented in the schema with defaults and cross-references to list_agents. The description adds no parameter-level detail beyond that, so the 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?

States a specific verb+resource: creating a persistent delegation session in a workspace. The clause 'without running a task yet' usefully separates it from the task-executing sibling delegate_task, though it never names that sibling explicitly.

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 directs the follow-up step ('Follow up with send_message to keep the agent's context between calls'), which is the key lifecycle guidance. It does not state the converse case for delegate_task or list any exclusions.

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 only annotation is openWorldHint=true, so the description carries the burden and does so well: it discloses the security policy that still applies to grants (sensitive-file protection for edits, no git history changes for shell), that grants are per call, and what the agent returns. This is behavioral context the annotations cannot supply.

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, front-loaded with the core action and the return contract, with no filler. Dense but each clause earns its place; the security caveat could be tightened slightly.

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 an 8-parameter tool with no output schema, the description supplies the return keys and the permission model well. It omits how the returned session_id relates to the sibling tools (e.g. whether the session can be continued via send_message), which is a meaningful gap given 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema by explaining that allow_edits/allow_bash are per-call grants that remain subordinate to the bridge security policy, and that paths are hints not restrictions.

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 ('Delegate a software-engineering task to an OpenCode agent') and describes the execution model (runs in the same workspace, explores the repository itself). Clearly distinguishable from the session-management siblings like create_session and 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?

Implies when to use it (offload a self-contained engineering task to a sub-agent) and notes per-call permission grants, but never names an alternative or a when-not condition. With siblings like send_message and get_diff available, the agent must infer that this is for new delegated work rather than continuing an existing session.

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?

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description adds that the diff is sourced from OpenCode via a specific endpoint, which is useful context, but says nothing about diff format, size limits, or behavior for sessions that made no changes.

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?

One tight sentence with the core action front-loaded; the trailing endpoint parenthetical earns its place by naming the data source, though it could be trimmed.

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 one-parameter read operation with no output schema, the definition covers the essentials. However, the actual return shape of a 'diff' is never characterized, which is the one thing an agent calling get_diff would most want to predict.

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 the single session_id parameter is fully described there, so the description does not need to compensate. It adds no format or sourcing detail beyond what the schema already states.

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: 'Return the file changes made by a delegated session', with the source pinned down ('as reported by OpenCode'). It distinguishes itself well enough from get_session (metadata) and list_agents, though it never names a sibling explicitly.

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 stated, and no alternatives named. The only routing hint is indirect, coming from the schema note that session_id comes from delegate_task/create_session.

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 readOnlyHint annotation already covers the safety profile, and the description adds useful behavioral nuance: the stored session state is always returned, while live OpenCode status is only included when a server is running. This conditional behavior is valuable context beyond the annotation.

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 with no filler. The main purpose is front-loaded, and the sibling reference to get_diff earns its place by clarifying tool boundaries.

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 read-only tool with one well-documented parameter, the description provides sufficient invocation context. It could name the fields contained in 'stored state' or describe the no-server behavior more explicitly, but those are minor gaps given the schema and readOnlyHint.

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 the session_id parameter is already well-described as the ID returned by delegate_task/create_session. The description itself adds no further parameter meaning, so the baseline 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 uses a specific verb ('Return') and names the exact resource: the stored state of a delegated session plus live OpenCode status. It also distinguishes itself from get_diff by telling the agent to use get_diff for file changes, which prevents confusion among siblings.

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 gives clear context for what get_session returns and points to get_diff as the alternative when inspecting file changes. It does not explicitly enumerate when not to use get_session, but the comparison to get_diff provides enough routing guidance.

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 readOnlyHint annotation already covers the key safety behavior Photon, so the description does not need to restate that. It adds useful context by mentioning project-local agent discovery from .claude-opencode/agents and the role of cwd. It does not describe output format or failure behavior, but no contradiction exists and the annotation lowers the burden.

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 sentence that leads with the core action and resource, then adds the most important scoping detail about project-local agents. Every part earns its place; there is no filler or 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?

This is a simple, read-only listing tool with no required parameters and no complex schema. The description plus the cwd parameter documentation is sufficient for an agent to know what the tool does and when to call it. The absence of an output schema is acceptable given the straightforward 'list' semantics.

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 only parameter, cwd, is already fully described in the schema with 'Workspace used to discover project-local agents (optional).' The description adds a small amount of context by linking cwd to the .claude-opencode/agents discovery mechanism, but schema coverage is 100%, so the baseline 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 names a specific verb ('List') and resource ('agents that delegate_task and create_session can use'), making the tool's purpose immediately clear. It also distinguishes this listing tool from the action-oriented siblings like delegate_task and create_session. The inclusion of project-local agents adds useful scope.

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 when this tool is useful: before delegating or creating a session, to discover available agent names. It names the consumer tools explicitly and clarifies the optional cwd behavior for project-local discovery, but it does not state formal exclusions or contrast directly with sibling listing tools.

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 only openWorldHint in annotations, the description carries the behavioral burden and does add real value: it discloses that the agent retains prior context and permission level, and that allow_edits/allow_bash mutate that level persisting into later messages. It does not describe errors on invalid/expired sessions or what the call returns.

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 tight sentences, zero waste, and the core action (continue an existing session) is front-loaded before the permission-state detail.

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 4-param stateful tool with no output schema and only an openWorldHint annotation, the description covers continuation semantics, context retention, and permission persistence adequately. Minor gaps remain around failure modes and return value, but nothing essential for correct invocation is missing.

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 four parameters, including the 'from this message onward' semantics of the allow_* flags. The description largely restates that, adding only the framing that the level change persists across messages – the baseline 3 for fully covered 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?

States a specific verb (continue/send) and resource (existing delegated session), and the phrasing 'Continue an existing delegated session' contrasts cleanly with the sibling delegate_task, which starts a new one. An agent can distinguish it from create_session and delegate_task without reading schemas.

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?

'Continue an existing delegated session with another message' establishes the context of use, and the session_id schema note ties it to delegate_task/create_session. It never explicitly says when NOT to use it (e.g. for a new task use delegate_task), so it falls short of full routing guidance.

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