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

Annotations declare destructiveHint=true/openWorldHint=true, but the description goes further: it discloses that only 'list' is non-mutating, that link tokens are shown once and never appear in grant listings, and that shares affect access outside the conversation. That is exactly the extra behavioral context the annotations cannot convey.

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?

A single dense paragraph that front-loads the highest-stakes constraint (confirmation for non-list modes). Every sentence carries information, though the run-on structure around the four modes could be broken for easier scanning.

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; the description instead covers the decision points an agent needs — mode selection, confirmation duties, and the one-time nature of link tokens. Nothing material is missing for a 7-param destructive 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 coverage is 100%, so the baseline is 3; the description earns an extra point by clarifying parameter interactions the schema states only individually — e.g. 'share' with mode 'link' mints a public link, and 'revoke' with vs. without grant_id produces entirely different outcomes.

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 ('Share one Configure project') and adds a distinguishing scope constraint ('without making a copy'). An agent can immediately tell this apart from the profile/connect siblings, none of which deal with sharing.

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?

Explicitly enumerates the four modes and their stakes, says which mode is read-only ('list only inspects'), and states when explicit user confirmation is required for each mutating path. It even distinguishes the two 'revoke' sub-cases and warns to confirm which is meant.

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