Revisionme

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

With no annotations, the description carries the behavioral burden. It discloses the return shape (Markdown brief, raw fields, screenshot image) and implies a read operation by omission of mutation, but it does not state that the call is non-mutating, whether the id must exist, error behavior for a missing id, or whether the screenshot is a link or inline image.

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 that front-loads the purpose and lists the returned components in a parenthetical. It is compact, though the parenthetical is dense and could be slightly tightened.

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 2-param read tool with no annotations and no output schema, the description adequately covers what is returned but leaves behavioral gaps (read-only nature, missing-id errors) and does not clarify the screenshot parameter's effect beyond implying an image is returned.

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 parameters have schema descriptions, so baseline is 3. The description adds the meaning of screenshot output (as an image) but does not add syntax or format 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 ('get issue', 'one report in full') and enumerates the returned fields, which is clearer than the sibling list_issues. It doesn't explicitly contrast with list_issues, but the singular 'one report' implied by the id parameter constrains to a single retrieval.

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 strongly implied by the required id parameter and the singular framing versus list_issues, but there is no explicit when-to-use or when-not statement. No prerequisites or claim that the issue must already exist 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?

With no annotations, the description carries the full behavioral burden. It does disclose ordering (newest first), the default filter (open), and a real permission trait ('every project the key allows'), which is meaningful. It stops short of anything about pagination/truncation, rate limits, or what a returned report contains.

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, no filler, with the ordering and default scope front-loaded so the agent gets the essential framing immediately.

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 3-param list tool with no annotations and no output schema, the description covers defaults and ordering but says nothing about the shape of a returned feedback report or how many items to expect. Adequate but leaves the agent guessing about the response.

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 limit, status, and project with their defaults. The description restates the status default ('open') and project scoping, adding no syntax or format detail beyond the structured fields. 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 the resource concretely ('feedback reports'), specifies ordering ('newest first'), and states the default result set ('the open ones across every project the key allows'). That is enough to separate it from get_issue (single item) and list_projects, though it never names those siblings 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?

Default behavior is clearly stated, which implies the common case (list open issues everywhere), but there is no explicit when-to-use guidance, no statement of when to reach for get_issue instead, and no mention of how to widen or narrow scope beyond the schema's own status/project fields.

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 does disclose one meaningful trait: results are scoped to what the API key can access. However, it says nothing about pagination, result ordering, or what happens when the key has no projects, which leaves real behavioral gaps for a list operation.

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 short sentence that front-loads the resource and scope and tacks the return detail on the end. No filler or redundancy.

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 no output schema, the description states the scope and the key returned field (ids), which is enough to invoke it correctly. It stops short of describing the full result shape (e.g., names or other fields alongside ids), a minor omission given the tool's simplicity.

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; the baseline of 4 applies. The mention of ids is about output, not inputs, so it does not add parameter meaning.

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 resource (projects/websites), the scope (those this API key can access), and the return content (their ids). It is clearly distinguishable from all siblings, which are issue-oriented (get_issue, list_issues, update_issue), so an agent can select it without ambiguity.

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: an agent infers it should call this to discover project ids, but there is no explicit when-to-use/when-not statement and no mention of alternatives. Since the sibling tools are unrelated (issues, not projects), no routing conflict exists, which keeps this at a viable 3 rather than lower.

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 for a mutation tool. It implies a partial update ('and/or'), but never states whether this requires write permission, whether it is idempotent, what happens to unspecified fields, or whether reopening a rejected issue is allowed. The 'and/or' hint is the only behavioral disclosure.

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; the verb and both mutable targets appear immediately. The nested parenthetical makes it slightly dense to parse, but nothing is wasted.

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 three-parameter mutation tool with no annotations and no output schema, the definition covers the status semantics adequately but leaves the 'important' parameter and the permission/idempotency profile unexplained. It is minimum viable rather than 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 coverage is only 33% (only 'id' described), so the description must compensate. It does explain all three status enum values with intent, which adds meaning beyond the bare enum list, but the 'important' boolean is named without saying what it affects, and there is no syntax/format 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 ('Set') and resource state ('status of a report') plus a secondary target ('the important flag'), so an agent knows this is a mutation tool. It does not explicitly contrast itself with the read-only siblings (get_issue, list_issues), though the update/read split is self-evident. Minor terminology drift: it calls the resource a 'report' while the tool and schema refer to an 'issue'.

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 parenthetical gives intent for each status value ('resolved after fixing it, rejected when nothing should be done, open to reopen'), which is real guidance on choosing a value. However it says nothing about when to reach for update_issue versus alternatives, nor about prerequisites such as permissions or who may reopen an issue.

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