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

Annotations already declare the non-read-only, non-idempotent, open-world profile, so the description's job is to add beyond that — and it does, disclosing the critical all-or-nothing semantics ('one unknown id and nothing is posted') and cross-thread linking behavior. It still omits permission requirements and any duplicate/limit handling.

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, front-loaded with the action and example before the atomicity caveat. Every clause carries information the agent needs.

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 mutation with an output schema (return shape need not be described) and safety annotations, the definition covers intent, batch scope, and failure atomicity well. Missing only secondary details such as auth scope and rate/size limits.

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%, so the description must compensate. 'Linked across every thread it names' and 'one unknown id' hint that comment_ids are thread identifiers and that invalid ids abort the call, but it never names the parameters, explains the message's 5000-char limit, or notes the 1-50 id bounds.

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 (report one spanned action as a single note) on a specific resource (multiple comment threads, linked), which is clearly distinct from single-thread siblings like post_reply. It never names an alternative explicitly, so differentiation is implied rather than spelled out.

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 example ('resolved 3 comments in PR #204') and the 'spanned several comments' condition, which tells the agent when batching applies. However, no exclusions are stated and no sibling tool is named as the single-thread alternative, so the agent must infer the boundary itself.

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 and openWorldHint=true, so the safety profile is covered. The description contributes real non-annotation behavior: PUBLIC visitor feedback is excluded by default unless 'source' requests it, which tells the agent the result set is filtered before it ever calls the 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?

Three short sentences, the core purpose and the most surprising behavior (default exclusion of public feedback) front-loaded. No filler, no repetition of the title.

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?

An output schema exists, so return values need no explanation, and annotations carry the safety profile. The description covers scope, filtering intent, and the non-obvious default. It is nearly complete, though it says nothing about result volume or ordering.

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 largely restates what the schema already documents for 'source' and adds only a plain-language version of the same default-exclusion rule, with no syntax or interaction 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?

States a specific verb and resource ('List feedback comments for a project'), which is unambiguous against siblings like get_comment (singular) and update_status/post_reply (mutations). It does not explicitly name or differentiate itself from those siblings, so it stops 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?

'Filter by status to find work to do' implies a usage context (triaging open work) but gives no explicit when-not or alternative-tool routing. No sibling is named, and 'use X instead when Y' guidance is absent.

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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuine conditional behavior: the text timeline is only returned 'when a session was recorded.' That discloses a variability in the response an agent otherwise could not predict, which is real value beyond 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?

A single front-loaded sentence opens with the core purpose, and the em-dash aside adds the response contents plus the agent-relevant reason for the timeline. Efficient overall, though the mid-sentence aside slightly complicates parsing.

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 correctly shoulders the job of describing return contents (repro context, thread, conditional timeline), and annotations cover the read-only safety profile. For a one-param read tool it is close to complete, missing only the commentId format.

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% and the single commentId parameter is undocumented in the schema, so the description carries the burden -- but it only implies the ID identifies 'one comment' and gives no format or sourcing guidance. With one self-naming parameter, this is minimally adequate rather than compensating for the 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 action and resource: retrieving full detail for one comment, enumerating what that detail includes (repro context, thread, timeline). It is clear about scope (single comment) but never distinguishes itself from siblings like fetch_feedback, so it lands at 4 rather than 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?

Usage is only implied: you call it to get detail on one comment, and the closing rationale hints at the value of a text timeline over an unwatchable replay. No explicit when-to-use condition, no exclusion, and no routing to alternatives such as fetch_feedback is provided.

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, open-world, non-idempotent, non-destructive profile. The description adds a genuinely useful behavioral fact beyond them: the note is visible to the reporter. It omits, however, that repeated calls will stack duplicate notes on the same thread (non-idempotent), which an agent would benefit from knowing.

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 an inline example; nothing is wasted. The example arguably earns its place by showing expected message content.

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 and only two simple required params, so the bar is modest, but a mutation tool with 0% param documentation should do more than state the intent: it never clarifies the commentId's origin or the effect of repeated replies.

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%, so the description must carry the burden, and it largely does not: commentId is never explained, and message semantics (the 1-5000 char limit, whether markdown is allowed) are only loosely hinted at by the example string.

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 (add a note to a comment thread) and gives a concrete example message. It does not differentiate itself from the sibling create_batch_note, which likely has an overlapping purpose, 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?

The phrase 'so the reporter can see what happened' implies the situation for using it, but there is no explicit when-not guidance and no routing to alternatives such as create_batch_note or update_status.

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 readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description adds a non-obvious authorization constraint (agent cannot confirm/approve) that annotations cannot express, which is genuinely valuable. It stops short of explaining what a successful transition returns or whether RESOLVED actually closes the comment given the approval caveat.

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 the action and its values front-loaded, followed by the single most load-bearing constraint. 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?

With an output schema present, return values need not be described, and annotations already cover idempotency and non-destructiveness. The authorization caveat fills the main behavioral gap. Minor residual ambiguity remains about whether an agent may ever set RESOLVED, since the enum permits it while the text says only the reporter can confirm a fix.

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%, so the description must carry the burden. It names the two status values (already in the enum) and hints at the semantics of confirming a fix, but says nothing about commentId or its format/scope. Partial compensation for an undocumented parameter set.

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 ('Move a comment to IN_PROGRESS or RESOLVED') and enumerates the allowed target states, so the agent knows exactly what the tool mutates. No sibling (get_comment, fetch_feedback, post_reply, create_batch_note) performs status transitions, so the operation is unambiguously distinct.

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 draws a permission boundary: agents cannot approve, only the reporter can confirm a fix. This tells the agent a class of action is off-limits. It does not, however, say when to prefer IN_PROGRESS versus RESOLVED, so the transition guidance is only partially supplied.

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