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

readOnlyHint=true already declares this is a safe read, and the description is consistent with that. It adds that each mode 'Returns' either all prompts or full text/details, but says nothing about permissions on workspace-scoped custom prompts, result size, or pagination. With an output schema present, the return-format gap is minor, so a 3 is appropriate.

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?

Front-loaded enumeration with one bullet per operation and an explicit 'Returns' line each; the structure makes scanning easy. The repetition of 'Returns:' and the near-duplicate public/custom pairs cost a little efficiency, but nothing is filler.

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?

All five parameters are exercised in at least one documented call pattern, and a return-value schema exists so return format needn't be restated. What's missing is behavior when required combinations are incomplete (e.g., prompt_details without prompt_id) and whether workspace_id is required for custom prompts.

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 0%, so the description carries the whole burden and largely does: it maps request='menu'/'prompt_details', prompt_id, prompt_type='custom', is_custom, and workspace_id to concrete call shapes. The gap is the unexplained overlap between prompt_type='custom' and is_custom=True in the two custom paths, and what happens if only one is supplied.

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 resource (Instagram prompt catalog) and enumerates the four operations it supports, each with the exact request/parameter shape. This clearly separates it from the generic siblings (execute_action, query_data, query_contexts), though it never explicitly says so.

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?

Each of the four call patterns doubles as when-to-use guidance: 'menu' for listing, 'prompt_details' for full text, plus the custom-vs-public branch. It's clear which mode to pick for each intent, but there's no stated exclusion or fallback if the caller's workspace/prompt_id is unknown.

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