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

With no annotations, the description carries the full burden, and it does add useful return-shape context (each message includes its channel id) plus the reply workflow. However, it never states that reading consumes/marks messages as read, nor any permission or rate-limit behavior — the read-state side effect is only inferable from the schema's peek parameter.

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: purpose first, then when to use, then what comes back and how to act on it. No filler or repetition.

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 tool with no output schema, the description covers purpose, trigger conditions, and the key returned field (channel id). Only the read-state side effect of the call is left to the schema, which is a minor 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 description coverage is 100% and the single parameter (peek) is fully documented in the schema. The description adds no meaning beyond it, 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 states a specific verb (Read) and resource (Slack messages that @mentioned the bot) with an explicit filter (not yet read). This cleanly distinguishes it from every sibling, which are all send/update/status write tools.

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 two concrete triggers: sessions started without --channels that cannot receive notifications, and catching up on missed messages. It also routes the follow-up action to send_slack_message. No explicit 'do not use when' exclusion is given, keeping it 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the supported markdown constructs, which is useful, but says nothing about permissions/scopes required, rate limits, or what happens when the channel already has a canvas — a behavior the schema's title description hints at but the prose ignores.

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 routing guidance, then the content-format detail. 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 a no-annotation, no-output-schema creation tool the description covers purpose, routing, and input format adequately. It omits the pre-existing-canvas behavior and any indication of what the caller gets back (e.g., a canvas ID), which are the remaining meaningful gaps.

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 real meaning for the markdown parameter by enumerating supported syntax (headings, lists, checkboxes, bold, code), going beyond the schema's terse 'canvas body, as markdown'.

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 ('Create a Slack canvas in a channel from markdown') and implicitly separates itself from send_slack_message by framing the artifact as durable reference material rather than a scrolling message. An agent can tell exactly what this produces 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?

Gives clear when-to-use guidance ('reference material people will come back to — a checklist, a runbook, a spec') and an explicit when-not ('rather than a message that scrolls away'). It stops short of naming a sibling tool by name, but the contrast against messaging is unambiguous.

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 usefully discloses that uploads render inline and that the path must be a file on this machine, but says nothing about required Slack scopes, file size/type limits, failure behavior, or what the tool returns on success.

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 and its distinguishing behavior. Every sentence carries information: what it does, when to use it, and the path constraint.

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 five-parameter upload tool with no annotations and no output schema, the description covers purpose, usage, and the key input constraint well enough to call it correctly. The main residual gap is post-call behavior (success result, error cases), which is not covered anywhere else.

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 five parameters (title, channel, comment, file_path, thread_ts) are already documented in the schema. The description only reinforces file_path's local-file constraint and adds no new syntax or format detail beyond that baseline.

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 (upload) plus resource (a local image/file into a Slack channel) and it states the distinguishing outcome: content appears inline rather than as a link. That implicitly separates it from send_slack_message, though no sibling is named outright, so it falls short of a 5.

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?

"Use for screenshots, diagrams and charts" gives explicit positive usage context, and the inline-vs-link framing hints at when to prefer this over send_slack_message. There are no stated exclusions or prerequisites, so it is clear context without the when-not guidance that would earn 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?

With no annotations, the description carries the full burden, and it delivers key behavior: it returns the message timestamp (ts) and explains the chaining pattern with update_slack_message for keeping a progress marker to one line. It omits permissions/auth needs, rate limits, and failure behavior, so it is substantive but not complete.

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, front-loaded with the core action and the return-value/chaining contract. The second sentence is somewhat dense with a nested clause about the progress marker, but every part 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?

There is no output schema, so the description correctly fills the gap by naming the return value (ts) and its use. Combined with 100% schema coverage on inputs, an agent has nearly everything needed; only auth/error context 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 channel, text, and thread_ts are already fully documented in the schema, including markdown conversion and length-splitting. The description adds no parameter-level detail beyond that, 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 ('Send a message to a Slack channel') and further scopes it to replying to incoming webhook channel messages. It implicitly separates itself from update_slack_message (rewrite) and send_slack_image (images) by naming the former as the follow-up step.

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 clear use case ('reply to webhook channel incoming messages from Slack') and points to update_slack_message for later rewriting. It stops short of explicitly stating when NOT to use this tool (e.g., use send_slack_image for images, update_slack_message for edits), so the agent must infer the alternatives from sibling names.

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 and does well: it discloses the single-message rewrite model, the ts handoff between calls, and the meaning of every status. It omits permissions/auth needs, rate limits, and failure behavior, which keeps it from a 5.

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 concept before the mechanics and the status vocabulary. Nearly every clause earns its place; only the trailing status enumeration is somewhat redundant with the schema enums.

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 stateful tool with no output schema and no annotations, the description covers the lifecycle and statuses adequately, and the remaining parameters (title, footer, advance, thread_ts) are well documented in the schema. Minor gaps remain around permissions and error cases.

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 ts, steps, update, advance, title, footer, thread_ts and channel. The description reinforces the ts/steps/update relationship but adds no syntax or constraints beyond the schema, 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 gives a concrete, vivid verb+resource: a live Slack checklist kept to one self-rewriting message, plus the create/update lifecycle. It is clearly not a generic message tool, though it never names a sibling (e.g. update_slack_message) to sharpen the distinction.

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 states the calling pattern explicitly ('call once with steps... call again with that ts and update') and the intended context ('any job with several stages', replacing a run of 'doing X now' messages). No explicit when-not or named alternative, so it stops 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?

With no annotations, the description carries the full burden and does well: it discloses diagnostic outputs (connection state, watcher status, queued messages) and the behavioral consequence of the watcher not running ('nothing inbound reaches this session'). It does not mention any read-only guarantee or side effects, but the diagnostic nature is clear from context.

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 front-loaded with the core diagnostic purpose and then lists the specific things checked. It is slightly long but every clause adds distinct information; no filler or repetition.

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-parameter diagnostic tool with no annotations and no output schema, the description fully compensates by detailing what the tool checks and when to call it. An agent has everything needed to invoke it correctly and interpret the results.

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 zero parameters, the baseline is 4. The description correctly indicates no inputs are needed and focuses on outputs instead, which is appropriate for a no-arg diagnostic tool.

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 (check the Slack bridge end to end) and enumerates exactly what it returns: connection state, mention watcher status, queued message count, and other connected projects. This clearly distinguishes it from siblings like check_slack_inbox or send_slack_message, which perform different operations.

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 explicit when-to-use guidance: call it first when Slack seems unresponsive or after starting a session, and explicitly says 'instead of guessing'. This gives the agent a clear decision rule that no sibling tool provides.

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 and does disclose the critical behavioral constraint (bot-authored messages only) plus replacement-not-append semantics. It is silent on failure modes for stale/deleted timestamps and Slack update rate limits, which leaves a real gap for a mutation tool.

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?

Front-loaded with the core action in the first clause, and each subsequent sentence carries distinct value (usage pattern, rationale, constraint). The illustrative status-marker example is slightly long but is the justification for the tool's existence.

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 no-annotation mutation tool with no output schema, the description covers what to rewrite, how to obtain the identifier, the recommended pattern, and the authorization boundary. Missing only error/edge behavior (non-bot messages, expired timestamps).

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 three parameters are already documented, including that ts comes from send_slack_message and that text is a full replacement. The description reinforces the ts provenance but adds no new parameter semantics beyond the schema baseline.

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 (rewrite) and resource (a message already posted), plus the key identifier (timestamp from send_slack_message). An agent can distinguish this from send_slack_message, send_slack_image, and slack_progress 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?

Gives an explicit workflow (post 'working on X', update as work moves, update once when done) and names the anti-pattern it replaces ('far better than posting a new message per step'). It also states the hard precondition: only messages this bot posted can be rewritten.

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