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

Annotations already declare readOnlyHint=true, and the description's 'browse'/'list'/'fetch' framing is consistent with that safe-read profile. It adds the useful distinction between public/system prompts and workspace prompts, but says nothing about pagination, result limits, or what a missing prompt_id yields. With annotations carrying the safety profile, this is adequate but not rich.

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?

One framing sentence followed by a two-item numbered list – front-loaded, scannable, and free of filler. The numbering maps cleanly onto the request enum, though the compressed phrasing ('Set is_custom=True + workspace_id for workspace prompts') is slightly telegraphic.

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?

An output schema exists, so return values need no explanation here. For a 5-parameter read-only catalog tool, the description covers the operation split and the mode-conditional parameters, which is everything an agent needs to construct a valid call; only the prompt_type value space remains undefined and that is minor.

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 0%, so the description must carry the parameter burden, and it largely does: it explains both request enum values, when workspace_id and prompt_type apply (menu), and when prompt_id and is_custom apply (prompt_details). The gap is prompt_type, whose accepted values are never hinted at, and is_custom is only explained for one mode.

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 ('Browse the Bing Webmaster Tools prompt catalog') and then splits it into the two concrete operations it supports (listing vs. fetching a prompt body). An agent immediately knows what domain this covers; the only thing missing is any explicit contrast with the sibling tools, which are named differently enough (execute_action, query_data) that confusion is unlikely.

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 two request modes are laid out as numbered cases with the condition that selects each one: 'menu' for listing, 'prompt_details' for fetching a body by prompt_id, plus the extra condition of is_custom=True + workspace_id for workspace prompts. There are no explicit exclusions or 'use X instead' guidance, but the mode split effectively serves that routing role.

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