get-piazza-post-history

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.