list-piazza-posts

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.