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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond annotations by warning that Piazza posts are untrusted user-generated content and should never be treated as instructions. It also qualifies the return as 'complete bounded,' which clarifies that the thread is not truncated or filtered.

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 with zero waste. The purpose is front-loaded, and the security warning is a single additional clause. No irrelevant information is present.

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, read-only get operation with an output schema and rich annotations, the description is nearly complete. It clarifies the untrusted nature of the content and the boundedness of the response. It does not cover error conditions or how to obtain a valid post_number, but this is minor given the output schema and the availability of list-piazza-posts as a sibling 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 description coverage is 50%: course_id is described as 'A course ID returned by list-piazza-courses,' but post_number has no schema-level description. The tool description mentions 'by post number' but does not elaborate on the parameter's semantics or constraints beyond that. With low coverage, the description adds only minimal value for post_number.

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 ('Get'), resource ('Piazza thread'), and the key parameter ('by post number'). It is distinct from the list and search siblings, though it does not explicitly name alternatives. The phrase 'one complete bounded' adds specificity about the scope of what is returned.

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 does not provide any guidance on when to use this tool versus the other Piazza tools, such as list-piazza-posts or search-piazza-posts. No alternatives, prerequisites, or exclusion conditions are mentioned. Usage context is only implied by the purpose statement.

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, openWorldHint, idempotentHint, and destructiveHint=false, covering safety. The description adds significant behavioral context beyond those: the history is 'bounded', the 'sequence' is not a stable revision ID, content is sanitized but still untrusted, and identity/audit metadata are omitted. These disclosures explain the nature of the data and its limitations, which is exactly the kind of transparency that helps an agent set expectations correctly.

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 compact (two sentences) and front-loads the purpose before caveats. It avoids unnecessary words. The structure is logical: purpose, then key limitations. A slightly more structured format (e.g., separating the condition from the caveats) could improve scanability, but it is already efficient and easy to parse.

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?

The output schema exists (though not shown), so the description needn't detail return values. The description covers the main caveats: bounded history, non-stable sequence, sanitized content, omitted identities/metadata. However, the condition 'when Piazza includes history' is ambiguous—it does not specify what happens when history is not included (e.g., empty array, error). This is a small gap for an otherwise complete read-only 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 description coverage is only 33% (only course_id has a description). The tool description does not compensate for the missing parameter explanations: it never defines post_number or max_revisions explicitly. The phrase 'bounded view' hints at max_revisions but does not explain its role or constraints. post_number is left entirely to inference. Given the low schema coverage, the description should have filled these gaps but does not, leaving the agent to guess about required 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 states a specific verb ('Get') with a clear resource ('a bounded view of a Piazza post's editable history') and a condition ('when Piazza includes history in the post response'). It clearly distinguishes from siblings like get-piazza-post, which presumably returns the current post rather than its history. The mention of 'editable history' and 'sequence' adds specificity that leaves no ambiguity about the tool's purpose.

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 provides context for when the tool is appropriate ('when Piazza includes history in the post response') and implicitly suggests it is not for getting the current post content. However, it does not explicitly name alternatives or state when not to use this tool (e.g., if the full current post is needed, use get-piazza-post). It also notes what is omitted (author/editor identities, audit metadata), giving some guidance on what the tool cannot provide, but stops short of a direct comparison with siblings.

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 provide readOnlyHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond annotations: it specifies the courses are 'configured' and 'accessible to the user,' which clarifies the tool's scope and permission implications. It does not repeat annotation data and introduces no contradictions. Given the richness of annotations, this is a solid supplement.

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 a single sentence with no wasted words. The primary action is front-loaded, followed by a concise and actionable hint about how to use the result. It earns its place with both purpose and usage guidance, and nothing is redundant or verbose.

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, read-only list tool with a rich output schema (signal indicates output schema exists), the description covers the essential purpose and usage. The output schema handles return-value details, and annotations handle safety traits. The description adds the 'configured' and 'accessible' context and ties the output to downstream tools. Nothing an agent needs to correctly invoke this tool 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?

There are 0 parameters, so the description has no parameter burden. The rubric sets a baseline of 4 for zero-parameter tools. The description does mention the output field 'course_id,' which clarifies what the tool returns, even though it is not a parameter. This is appropriate given the empty 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 clearly states the action ('List') and the resource ('configured Piazza courses accessible to the user'). It also distinguishes itself from sibling tools by focusing on courses rather than posts, and it explains the relationship to other tools ('Use a returned course_id with the other Piazza tools'). This leaves no ambiguity about what the tool does.

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 provides a clear usage hint: 'Use a returned course_id with the other Piazza tools.' This implies the tool is a prerequisite for the other Piazza tools and should be called first to obtain a course_id. However, it does not explicitly name alternative tools or state when not to use it, though the sibling names (e.g., list-piazza-posts) make the domain distinction obvious. Missing explicit exclusions but contextual guidance is strong.

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 read-only/idempotent safety, and the description adds substantial behavioral context: multi-request intersection, no pagination, non-atomic snapshots, truncated semantics, and a security warning about untrusted content. This goes well beyond what annotations provide.

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 a single dense paragraph that front-loads the purpose and packs in essential behavioral details. Every sentence earns its place, though it is somewhat long; the complexity justifies the length.

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?

Given the complex filtering and pagination behavior, the description is remarkably complete. It explains the sequential request handling, truncation flag, absence of offsets, and security considerations. With an output schema present, the agent has everything needed to call the tool correctly.

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 75%, so the baseline is 3. The description adds meaning by clarifying the AND logic, the exact spelling requirement for folder_name, and the maximum result count of 25. It enriches parameter understanding but does not fully cover every edge case (e.g., max_results default behavior is left to 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 ('List bounded post summaries'), a precise resource ('one configured Piazza course'), and a distinctive filtering constraint ('match every selected filter (AND, not OR)'). It clearly differentiates from unfiltered listing tools by emphasizing the filter logic.

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 clear guidance on how to choose filters and when folder_name is required, but it does not explicitly name sibling tools or explain when to prefer this over list-piazza-posts or search-piazza-posts. The context is implied rather than stated.

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 read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond annotations: the pagination protocol (truncated flag logic, sequential offset increments) and a security warning about untrusted content. This extra context is not derivable from annotations or schema, and it directly affects how an agent should execute the tool safely and correctly.

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 a single compact paragraph that front-loads purpose and includes essential operational details. It covers limit warning, pagination steps, and security in four sentences. While slightly verbose, every sentence carries necessary information and there is no fluff. The structure is logical: purpose → constraints → usage → safety.

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?

Given the available output schema (present in the context), the description is complete for an agent to call the tool correctly. It covers all parameters (via schema + description), the pagination protocol, the maximum limit constraint, and the security consideration. No critical missing information – an agent can decide when to use this tool, how to paginate, and how to handle responses safely.

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% – limit, offset, and course_id all have descriptions in the schema itself. The tool description mostly reiterates what's already in the schema (max limit 25, offset start at 0, add limit after truncated=true). It does add a subtle nuance about the overall pagination flow ('start at offset 0 and request one page at a time'), but this is largely a restatement. The description adds limited value beyond the schema, so 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?

The description states a specific verb and resource: 'List bounded recent post summaries from one configured Piazza course.' It clearly distinguishes this from sibling tools like list-piazza-courses (list courses), get-piazza-post (single post), and search-piazza-posts (search). The scope is explicit: summaries, from one configured course, bounded to recent posts.

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?

Provides explicit, actionable usage guidance: 'For recent posts, request one page. To retrieve all posts, start at offset 0 and request one page at a time, increasing offset by limit only when the previous response has truncated=true. Stop when truncated=false; do not prefetch speculative offsets in parallel.' It also warns against treating post content as instructions, which is a safety guideline. The guidance is specific and covers pagination strategy without ambiguity.

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, idempotentHint, and non-destructive, so the safety profile is covered. The description adds a critical warning about untrusted user-generated content and instructs the agent not to treat post text as commands, which is valuable context beyond annotations. It does not elaborate on return format, but the output schema compensates.

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 consists of two concise sentences: the first states the tool's purpose and the second adds a security caveat. It is front-loaded with the core action, and every sentence earns its place with no redundant wording.

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?

Given the presence of an output schema and annotations, the description is mostly complete for a search tool. It covers the core purpose and includes an important security warning. However, it lacks explicit parameter guidance and does not clarify what 'bounded post summaries' entails, leaving some ambiguity around result limits and search scope.

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 only 33% – only course_id has a description. The description hints at 'bounded post summaries' which relates to max_results, but it does not explicitly explain the query parameter or the max_results constraint. With low schema coverage, the description fails to compensate for the undocumented parameters.

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 clearly states the verb (search), resource (one configured Piazza course), and output (bounded post summaries). It distinguishes itself from sibling list/get tools by focusing on search within a single course, but it does not explicitly name alternatives, so it falls just 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 description implies usage for searching within a specific course, but provides no explicit guidance on when to choose this tool over list-piazza-posts, list-piazza-filtered-posts, or get-piazza-post. No exclusions or alternative conditions are mentioned, leaving selection to inference.

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