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

The annotations already establish that this is a read-only, open-world lookup, so the safety profile is covered. The description adds useful behavioral context beyond that: which chain is read (mainnet), what is compared (approvals against the threshold), when an approved proposal executes after the time lock, and a clear caveat that a single-wallet upgrade key makes warnings impossible. It also frames the result as 'Facts, not an audit', setting expectations about interpretation.

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 definition is front-loaded with the core question and then layers scope, outputs, limitations, and use-case phrasings in a logical order. Each sentence carries new information rather than restating the title. It runs slightly long for a one-parameter tool, but no sentence is clearly dispensable.

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?

There is no output schema, so the description carries the return-value burden, and it does so well by enumerating pending upgrades, authority changes, closures, approval counts versus threshold, time-lock timing, other open proposals, and the last multisig upgrade. It does not describe what happens for a program with no multisig at all or an invalid address, leaving a small behavioral gap. For a single-parameter read tool, it is otherwise complete.

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?

There is a single required parameter and the schema already documents it at 100% coverage as 'The program's address (base58)'. The description only implicitly clarifies that the address must belong to a program upgraded through a Squads v4 multisig, without adding format, validation, or edge-case guidance. With the schema doing the heavy lifting, the baseline of 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 uses a specific verb and resource: it reads a program's newest Squads v4 multisig proposals from mainnet and reports pending upgrades, authority changes, or closures. That is far more precise than a tautology, and it implicitly separates this from a general-inspection tool like program_inspect by scoping to multisig proposals. It stops short of naming or explicitly excluding any sibling tool.

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 definition gives concrete trigger questions ('is X about to be upgraded?', 'any pending upgrade for this program?', 'when was it last upgraded through its multisig?') and states the applicability constraint: the program must be upgraded through a Squads v4 multisig. It also declares the negative cases (single-wallet upgrade key, frozen program) where no warning is possible. The only gap is that it never names an alternative tool to use instead when this tool's prerequisites do not hold.

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