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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description usefully discloses that the result is session-scoped ('active for this session'), which the annotations do not convey, but it says nothing about the idempotentHint=false oddity, pagination, or result shape.

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 sentence with zero waste, front-loading the action ('List') and then the two pieces of information returned. Nothing could be trimmed without losing meaning.

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 parameterless read tool with readOnlyHint, the description covers what is listed and which account is flagged active, which is most of what an agent needs. With no output schema, a brief note on the result shape or ordering would make it fully self-contained.

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 is no parameter semantics to document; the baseline for a parameterless schema is 4. Nothing in the description is needed to clarify inputs.

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?

Specific verb 'List' plus resource 'configured accounts/services', and it adds the active-session detail. It does not name or contrast with siblings like janus_use_account or janus_whoami, but the scope is clear enough to distinguish a listing tool from a switching/identity tool.

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?

Implicit usage only: listing accounts naturally precedes janus_use_account, and the 'which is active for this session' phrasing hints at session-awareness. There is no explicit when-to-use, no exclusions, and no routing to alternatives such as janus_whoami.

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 only cover safety hints (readOnly=false, openWorld=true, destructive=false, idempotent=false). The description adds material behavior beyond that: a browser window opens, the token is captured locally and saved to the OS keychain, and it never passes through the chat. This is exactly the security-relevant context an agent needs.

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 tight sentences: action first, token-handling detail second, provider list last. No filler, and the most decision-relevant 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?

No output schema exists, so the description carries the return-value burden, which it does by explaining the token is saved locally and how to reference it afterwards. Combined with 100% schema coverage, an agent has everything needed to invoke 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% and both parameter descriptions already explain 'name' (used as oauth:<name>) and 'provider' (preset, e.g. github, google). The description largely restates this convention rather than adding new syntax or constraints, 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?

States a specific verb+resource (start OAuth login for a provider) and the side effect (store token as <name>). It is clearly distinguishable from siblings like janus_list_accounts or janus_whoami, which do not initiate auth flows.

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?

Tells the agent the follow-up step: reference the token via an account env as "oauth:<name>", and lists built-in providers (github, google, supabase). It gives clear context for when this tool is the right one, but doesn't explicitly state when not to use it or prerequisites (e.g., whether a browser must be available).

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 declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is already structured. The description adds genuinely useful side-effect context beyond that: the call reloads upstream tools and notifies the client, which tells an agent the tool list may change after invocation. It does not contradict the annotations.

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 short clauses, front-loaded with the core action before the side effects and the scope note. No filler or restatement of the name. The parenthetical default could be phrased more tightly, but nothing is wasteful.

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 two-parameter state setter with no output schema, the description covers purpose, side effects, and the scope default. Annotations carry the safety profile. The remaining gap is account_id semantics and any failure behavior for an invalid account, which keeps it short of fully 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 0% for two parameters, so the description must compensate. It does explain the scope enum values and its default ('defaults to the broker bindingMode'), which is real added value. The required account_id gets no semantics at all – no format, no hint that it should come from janus_list_accounts – leaving half the surface 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?

The description states a specific verb and resource: 'Set the active account/identity.' That is unambiguous and an agent can distinguish it from janus_whoami (read current identity) or janus_list_accounts. It does not explicitly contrast itself with the closest sibling, janus_with_account, which is a scoped variant of the same idea.

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?

Usage is implied by the name and by 'Set the active account/identity' – an agent can infer this is the tool to call when switching identity. However, there is no explicit when-to-use guidance, no statement of when to prefer janus_with_account or janus_login instead, and no mention of prerequisites such as needing an existing authenticated 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?

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real value by signaling that resolution provenance is returned ('how it was resolved'), but it does not explain the odd non-idempotent hint or the shape of the resolution 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?

A single tight sentence with the subject front-loaded and no wasted words. Appropriate size for a no-arg query tool.

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-param read tool with annotations covering safety, this is nearly adequate, but with no output schema the description should hint at the returned fields (account identity, resolution source) to fully prepare the agent.

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 is nothing for the description to disambiguate; baseline 4 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 states a specific verb ('Return') and resource ('the active account for this session'), plus the extra dimension of 'how it was resolved'. This is clearly distinct from siblings like janus_login or janus_use_account, though it never explicitly names or contrasts with 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?

There is no statement of when to call this versus janus_list_accounts or the other session tools. The phrase 'for this session' implies a diagnostic/context-check use case, but the agent must infer that entirely.

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=false, openWorldHint=true, and idempotentHint=false, so the safety posture is partly covered. The description adds the key non-obvious behavior that the active account is left untouched, but does not disclose side effects, auth requirements, or what happens to the invoked tool's writes. Adequate, not rich.

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 tightly written sentences with the primary behavior and its distinguishing constraint front-loaded, followed by the discovery fallback. No filler.

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 open-world meta-tool with no output schema, the description covers the core modes (invoke vs. list) and the account-scoping behavior well. It omits behavioral detail on the arbitrary tools it may invoke, which is a minor gap given annotations carry the safety profile.

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 four parameters are already documented in the schema. The description's mention of omitting 'tool' to list tools duplicates what the schema already states about the tool parameter, adding no syntax or format detail beyond it. 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 and resource ('Run a single tool call on another account') plus a critical scope constraint ('WITHOUT changing the active account') that implicitly separates it from the sibling janus_use_account. An agent can tell what this does and what it is not without opening any schema.

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 'WITHOUT changing the active account' clause establishes clear context for when to use this over janus_use_account, and the description instructs how to discover tools ('Omit tool to first list that account's available tools'). It stops short of naming the alternative sibling explicitly or stating exclusions.

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