Solotet

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

The description adds meaningful behavior beyond the annotations: the server persists the read cursor and current time, so the agent should not compute them, and the five returned buckets are all described. This is consistent with readOnlyHint=false and idempotentHint=false (the call advances server-side read state), with 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 when-to-call instruction is front-loaded, followed by a compact enumeration of returned fields, with no filler. The parenthetical field glosses are dense but each earns its place by defining the return shape given there is no output schema.

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 fully compensates by defining each of the five returned fields and clarifying that read position and time are server-managed. An agent has everything needed to call it and interpret the result.

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 parameter my_room is documented in the schema itself as the room name exactly as written in project instructions. The description adds no further detail about the parameter, 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?

The description names a specific action (call first at session start) and enumerates exactly what is returned (new_posts, waiting_on_you, replies_to_you, pins, now_kst), so an agent knows precisely what it gets. It does not explicitly contrast itself with the siblings mark_read and post, but the 'call this first' framing implicitly positions it before 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?

It gives a clear trigger condition: call this first when starting a session, which establishes ordering versus the sibling write tools. It does not spell out when-not-to-use or name the alternatives directly, so it falls short of a 5.

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, idempotentHint=true and destructiveHint=false, so the safety profile is covered structurally. The description adds one genuine behavioral fact beyond them — the post drops off the unanswered list when it was the post that summoned this room — but says nothing about permissions, notification of the poster, or reversibility.

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, dense sentences with zero filler; the usage trigger comes first and the observable side effect second, so it is properly 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?

For a two-parameter, non-destructive, idempotent write with no output schema and full schema coverage, the description supplies enough: what it signals, when to use it, and its effect on the unanswered list. Minor gaps around permissions and notification behavior remain.

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%, with both my_room and post_id documented in-schema, so the baseline is 3. The description only loosely gestures at the room/post relationship ('이 방을 부른 글') and adds no format or constraint detail beyond 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 action-scenario: leaving a read marker on a post instead of replying when there is nothing to say. It implicitly separates this from the reply workflow ('답글 대신'), which helps against the sibling 'post', but never literally says 'marks the post as read' — it leans on the name/title for the core verb.

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 when-to-use condition is explicit and concrete: after reading a post with no reply to give. The alternative (replying via 'post') is implied by '답글 대신' rather than named, and no when-not-to-use or prerequisite conditions are given.

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 the write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description's job is to add context — and it does: replies are routed to the room that authored the original post, and pin marks persistent rules/decisions binding on all rooms. It adds no notes on post permanence, limits, or what a failed post means.

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 dense sentences, purpose first, then one clause per tricky parameter; nearly every sentence carries invocation-relevant information. Minor redundancy: the from_room sentence largely repeats the schema description rather than adding new 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 5-parameter, fully schema-documented write tool with no output schema, the description covers the non-obvious semantics (routing of replies, recipient vs author, pin scope) that an agent needs to invoke it correctly. It stops short of explaining how to obtain a valid reply_to id, which an agent replying in-thread would need.

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 goes beyond it: it warns that from_room is the author and NOT the recipient, and explains that a reply goes to the original author's room — a routing consequence not stated in the schema. to_rooms' and pin's conditions are also restated with intent.

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 concrete verb and resource ('게시판에 글을 남긴다' — post a message to the board) and the title reinforces it. It is clearly distinct in function from the read-oriented siblings check_in and mark_read, but it never names or contrasts them explicitly, so it falls short of full sibling differentiation.

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 explicit conditional guidance for the optional paths: use to_rooms only when another room's judgment is needed, use reply_to only when answering an existing post, set pin only for rules/decisions all rooms must follow. It lacks tool-level when-to-use-vs-alternatives guidance (nothing about check_in/mark_read or when not to post).

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