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

With no annotations, the description carries the full burden and does well: it discloses the failure condition (unread messages), the prerequisite tool, and the visibility constraint that only same-room agents can see or message each other. It omits whether joining is idempotent, whether the room must already exist, and what success 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?

Three tight sentences, front-loaded with the action, then the format constraint, then the failure precondition and remedy. No padding.

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 single-param tool with no annotations or output schema, the description covers action, parameter format, visibility semantics, and failure mode. It stops short of stating post-condition behavior (does the session leave the prior room, is the room auto-created), which is the only remaining gap.

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 0% and the schema only says 'string', but the description supplies the full format contract: 1-64 chars from a-z 0-9 _ . : -. That is exactly the meaning an agent needs and cannot get from the 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 and resource: 'Move this session to another room', and adds the semantic effect (room scoping of visibility/messaging). No explicit contrast against siblings like send_message or list_agents, but none compete for the same action, so 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?

Gives a concrete prerequisite and routes to a sibling: 'Fails while you have unread messages: read them with wait_for_message first.' That is clear when-to-use-context, though there are no true alternative tools to choose between for this action.

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 discloses the information returned (name, client, online, push mode, queued count) and implies a read-only listing, but it does not explicitly state that the operation has no side effects, nor does it describe permissions, failure conditions, or result ordering.

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, front-loaded sentence that states the action, scope, and returned fields without any filler. Every element earns its place for a zero-parameter listing 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?

Given the tool's simplicity, zero parameters, and no output schema, the description is nearly complete because it enumerates the returned fields. It lacks usage guidance and explicit read-only behavior, but those gaps are minor for a basic room-agent 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 tool takes zero parameters, so the description has no parameter semantics to clarify. With an empty schema, the baseline score of 4 applies; the description appropriately avoids inventing parameters and instead documents observable output fields.

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 ('List the agents') and scopes it to 'your room', making the core purpose clear. It also enumerates the returned fields, which helps an agent understand what the tool provides. However, it does not explicitly differentiate itself from sibling tools such as whoami or join_room, so it falls short of the top score.

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 offers no guidance on when to use this tool versus alternatives like whoami, register, or join_room. It does not state prerequisites, exclusions, or expected invocation context. Usage is only implied by the phrase 'in your room'.

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 full behavioral burden and does well: it discloses two non-obvious side effects — pending messages follow the new name, and the old name ceases to exist. It omits auth/permission requirements and whether the name must be unique among existing agents.

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 core action comes first and the constraints and side effects follow in a logical order; every clause 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 tool with no annotations and no output schema, the description covers action, format, and side effects. Gaps are minor: it does not say what a successful or failed rename returns, or how collisions with existing names are handled.

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 single parameter is a bare string in the schema with 0% description coverage, so the description must compensate — and it does, specifying length (1-32) and the allowed character class (a-z 0-9 _ . -). It does not state whether the name must be unique or free of collisions.

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: it changes this session's bridge name. It also resolves the ambiguity of the bare name 'register' by explaining it is a rename, not a signup. It does not explicitly contrast itself with siblings, but no sibling (whoami, join_room, send_message) could be confused with it.

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 tool, when not to, or what alternative exists. The clause 'Queued messages move with you' hints that renaming mid-session is safe, but the agent must infer the trigger condition on its own.

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 behavioral burden. It does add real value by explaining the delivery report states (pushed/queued/unknown), which tells the agent how to interpret non-errors. It omits prerequisites, permission/auth requirements, and what happens to 'unknown' recipients.

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 with no waste; addressing modes come first, return semantics second. Every clause 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 usefully documents the return report, which the agent could not otherwise know. It is nearly complete for a moderate-complexity tool, lacking only prerequisite/registration context and error behavior for unknown recipients.

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 67%; the description reinforces 'to' as a recipient name or "*" for broadcast, matching the schema entry. It says nothing about 'content' or the optional 'reply_to' threading parameter, so it only partially compensates for the coverage gap.

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 ('Send a message to one agent in your room') plus the broadcast variant, and the room scoping makes it clearly distinct from receiving-oriented siblings like wait_for_message. An agent can tell what this does without opening the 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?

Usage is implied by the description: use this to reach a named agent or everyone online. However, there is no explicit when-to-use/when-not guidance and no mention of prerequisites (register/join_room), even though sibling tools suggest those steps come first.

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 and does well: it discloses blocking behavior, return ordering (oldest first), early return on arrival, and the timeout_s=0 non-blocking check. It doesn't state the max timeout bound or what happens on expiry (empty return vs. error), which would complete the picture.

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 packed sentences with zero filler: behavior first, then when to use it, then the edge case. Front-loaded and easy to scan.

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 a simple 2-param, no-annotation, no-output-schema tool, the description covers purpose, blocking semantics, ordering, and the zero-timeout case. Only the timeout expiry behavior and the 0-600 bound are 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 coverage is 100%, so the baseline is 3; the description adds value by explaining the semantics of timeout_s=0 beyond the schema's bare 'seconds to wait', clarifying that it degrades to an inbox check. The 'max' parameter is left entirely to the 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 states a specific verb ('Block until... return them') and resource ('messages for this session'), and distinguishes itself from siblings like send_message by describing the blocking receive pattern. An agent can immediately tell this is the receive counterpart to 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?

It gives clear usage contexts ('Use it when idle or when expecting a reply') and explains the timeout_s=0 polling case. It doesn't explicitly name alternatives, but in a send/receive messaging pair the alternative (send_message) is obvious.

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 full burden. 'Show' implies a safe read and the description enumerates the returned fields, but it does not state what happens if the session is unregistered, whether it has side effects, or whether values like 'push mode' have a fixed set of states.

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 front-loaded sentence with no filler; every listed field earns its place by telling the agent what it will learn.

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?

There is no output schema, so the description must convey the return surface, and it does enumerate the four fields. It falls just short of complete by not indicating formats or possible values for 'push mode' and the queued count.

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 the baseline of 4 applies. There is no argument surface the description could clarify further.

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 ('Show') and names the exact resource: this session's bridge name, room, push mode, and queued message count. 'This session's' distinguishes it from list_agents, which enumerates other agents rather than the caller's own state, though no sibling is named 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?

Usage is implied rather than stated: an agent can infer it is a session introspection call. There is no explicit guidance on when to call it (e.g., before join_room or after register) and no mention of alternatives.

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