ShipLog

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 disclose the key state behavior that entries are drafted unless publish is set, which tells an agent the write is staged rather than immediately live. It says nothing about required permissions, whether drafts are editable later, or what the call 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?

Two short sentences, front-loaded with the core action and followed by the most consequential parameter behavior. The 'captain's log' aside is decorative but does not obstruct comprehension.

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 simple four-parameter create tool with no annotations and no output schema, the description covers the essential draft-vs-publish distinction but omits what happens on failure, whether the entry is returned, and any prerequisite context. Adequate but with clear 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 all four parameters are already documented, making the baseline 3. The description reinforces the publish semantics ('set publish to true to publish it immediately') but adds nothing on category, content format, or title expectations beyond what the schema states.

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 ('Write a changelog entry') that an agent can immediately map to intent, and the parenthetical nickname reinforces the concept. It is clearly distinct from the read-oriented sibling list_changelog, though it never names that sibling 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?

The description gives useful operating guidance for the publish flag (draft by default, set true to publish immediately), which implies a draft-then-publish workflow. It does not, however, say when to prefer this tool over siblings like create_feedback or update_feedback_status, leaving usage context implied.

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. It says nothing about permissions or auth needed, whether duplicate submissions are deduplicated, whether the item lands in a pending state, or what the call returns after the write — all material for a create 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 front-loaded sentence with zero filler. It is efficient, though its brevity verges on under-specification for a write tool rather than excess.

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 annotations and no output schema, the description is the only source of behavioral context, and it omits return value, side effects, and post-creation state. Parameter documentation is fully covered by the schema, but the mutation semantics are not.

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 four fields (title, author_name, description, author_email) are already documented, and only title is required. The description adds no meaning 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?

States a specific verb (Add) and resource (a feedback item) plus a destination (the project's board), which is enough to distinguish it from list_feedback, search_feedback, and update_feedback_status. It stops short of explicitly naming the sibling boundary, so it is clear but not fully differentiated.

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 use this versus searching, listing, or updating feedback, and no prerequisites or exclusions. Creation versus mutation is only implied by the verb 'Add'.

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. It discloses the shape of the response (counts plus top-voted items), which is the key behavioral fact, but never states that it is read-only, whether it is scoped to a project automatically, or how 'top-voted' is computed (time window, vote source).

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 waste. The return contents are front-loaded and the motivational use case follows, so an agent can stop reading after the first clause if that is all it 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?

With no output schema and no annotations, the description is the only source of return-shape information, and it leaves gaps: how many 'top-voted items' are returned, over what period, and whether counts include archived/closed feedback. Adequate as a starting point but not fully specified.

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 to disambiguate; the baseline of 4 applies. The description does not need to add argument semantics.

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 verb and resource ('Get an overview of the project's feedback') and enumerates what the overview contains: total count, counts by status, and top-voted items. This aggregate shape implicitly separates it from list_feedback/search_feedback, 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?

'The best starting point for "what should I build next?"' frames a usage scenario and implies it should be called before drilling in. However, it never names the alternatives (search_feedback, list_feedback) or states when this tool is the wrong choice.

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 it does disclose two real traits: result ordering (newest first) and default scope (drafts included). It says nothing about return shape, whether results are paginated beyond the limit cap, or that the operation is a side-effect-free read.

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, front-loaded with the verb and resource, with the useful scope facts packed into a trailing clause. 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 simple two-parameter read with complete schema coverage and no output schema, the description covers purpose, ordering, and default draft inclusion – enough to call it correctly. Only the semantics of combining the "including drafts" default with a status filter is left implicit.

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 both parameters (limit with default/max, status enum) are already fully documented, establishing a baseline of 3. The description adds no parameter-level detail beyond implying the unfiltered default includes drafts, which is inferable from the optional status param.

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 uses a specific verb+resource ("List the project's changelog entries") and adds scope qualifiers ("newest first, including drafts") that tell the agent exactly what a call returns. Sibling tools are all feedback- or create-oriented, so no explicit differentiation is needed or supplied.

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 by the verb: any time an agent needs to browse changelog entries. There is no explicit statement of when to prefer this over a filtered lookup or how it relates to create_changelog_entry, and the interaction between the default "including drafts" and the optional status enum is left for the agent to reconcile.

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; "List" implies a read-only operation but that is inference rather than disclosure. It adds the default sort (votes), yet says nothing about pagination totals, return shape (no output schema), or whether status filtering interacts with sorting.

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, front-loaded with the resource and its default ordering, then the use case. No filler or restated metadata.

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?

Covers what the tool returns at a high level and its default sort, which is adequate for a simple read tool with full schema coverage. However, with no annotations and no output schema, an agent still lacks any statement about response contents (e.g., whether vote counts and statuses are included) or result-set size behavior.

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 all four parameters are already documented, establishing the baseline of 3. The description adds one useful detail the schema omits — that sorting defaults to votes — but does not clarify offset/limit interaction or status semantics.

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 the project's feedback items") plus the default ordering, so the agent knows exactly what it retrieves. It does not distinguish itself from siblings such as search_feedback or feedback_summary, 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?

"Use this to see what users are asking for most" gives an implied usage scenario tied to vote sorting. There is no explicit when-not guidance and no mention of when to prefer search_feedback or feedback_summary instead.

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 bears the full behavioral burden and does not carry it. It does not state whether matching is substring, case-insensitive, or ranked, what the results look like, or that the operation is read-only and non-destructive.

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 efficient sentence with the scope constraint front-loaded and zero filler. It borders on under-specification rather than being verbose, which keeps it from scoring lower.

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 search with no output schema and no annotations, the definition is minimally adequate. Missing details that matter here are matching semantics and result ordering, which an agent would want before relying on 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?

Schema coverage is 100%, with both query and limit fully documented in the schema, so the baseline is 3. The description adds only that the query applies to title and description fields, with no syntax or matching detail beyond that.

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 verb (Search) and resource (feedback items) and narrows the search scope to title or description. It implicitly contrasts with list_feedback, but never names that sibling explicitly, so the differentiation must be inferred.

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?

Mentioning search-by-keyword implies usage (use this when you have a term rather than browsing everything), but there is no explicit when-to-use vs. when-not guidance and no mention of list_feedback as the alternative for unfiltered retrieval.

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, and it discloses very little. It does not say whether status changes are reversible, whether transitions are restricted (e.g. can 'closed' go back to 'open'), whether permissions are required, or whether side effects like notifications occur. For a mutation tool with zero annotation coverage this is a significant gap.

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 parenthetical examples are slightly redundant against the enum but stay brief and aid quick scanning.

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 no output schema and no annotations, the description covers the core action but omits anything about valid transitions, return value, or side effects. Adequate to invoke, but thin for a state-changing tool.

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% with a required id and an enumerated status field, so the schema already documents both parameters fully. The description's examples ('planned, in_progress, completed') merely restate a subset of the enum rather than adding syntax or transition rules. Baseline 3 is appropriate.

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 ('Move a feedback item to a new status') that is unambiguous and distinct from the create/list/search siblings. The parenthetical examples partially duplicate the schema enum, and it doesn't explicitly contrast with siblings, but the action is clear on its own.

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 verb (use it when you want to change a feedback item's status), but there is no explicit when-to-use/when-not guidance and no alternative named. It works with no sibling named as an alternative, but it leaves the agent to infer.

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