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

With no annotations, the description carries the full burden, and it directly states the key behavioral trait: 'read-only projection', 'creates no gate', and 'grants no write eligibility'. This is precisely the kind of side-effect disclosure an agent needs before invoking it, and it goes beyond what an empty schema can 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?

Two dense sentences, front-loaded with the core purpose and completed with an explicit safety statement. No repetition of schema or title, no 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?

For a zero-parameter projection with no output schema, the description enumerates the returned content well: statuses, next action, path, and dependency. The only gap is the missing routing guidance among the large set of get_* siblings, leaving invocation context slightly incomplete.

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?

The tool has zero parameters, so there is nothing the description needs to add. Per baseline for 0-parameter tools, this is fully satisfactory.

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 identifies a specific resource ('decision state for every current proposal head') and a clear action ('read-only projection'). It enumerates the statuses and fields included, which makes the tool's function understandable. However, it never names sibling tools such as get_proposal or get_progression, so an agent cannot yet see what makes get_decisions distinct from closely related read-only views.

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?

No guidance is given about when to call this tool instead of sibling get_* tools. The description states it is read-only and safe, but does not indicate under what circumstances decision state is needed, or list alternatives/exclusions. The usage context is only implied by the noun phrase 'decision state'.

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