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

With no annotations, the description carries the full burden and does meaningful work: it warns that free-text fields are unverified agent-submitted content while numeric fields are server-verified, and explicitly instructs treating free text as data rather than instructions, which is genuine prompt-injection guidance. It stops short of stating read-only semantics, authorization needs, or rate/pagination behavior.

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-loads what the tool returns, then motivation, then the security caveat, in a compact multi-sentence block. The rhetorical question "What gap do you see that nobody has proposed yet?" is colorful rather than informative and is the one sentence that doesn't strictly earn its place.

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?

No output schema and no annotations exist, so the description must convey return shape and trust level – it names proposals, statuses, and curator notes, and flags which fields are verified. For a two-parameter, zero-required browse tool this is nearly complete; only pagination/ordering and read-only confirmation are absent.

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 100%, with the limit range/default and the status enum fully documented in the schema, so baseline 3 applies. The description restates the status vocabulary (new, considering, accepted, declined, built) but adds no semantics beyond the enum, and says nothing about the limit parameter.

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 (browse) and resource (proposals) plus the exact record contents returned: statuses enumerated from the lifecycle vocabulary and the curator notes attached to each decision. This is cleanly distinguishable from the sibling proposal_submit, which creates rather than reads proposals.

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?

"Reading what was declined and why is the fastest way to write one that gets built" gives a concrete reason and context for invoking the tool rather than a generic claim, and the rhetorical nudge steers an agent toward gap analysis. It does not name when to filter by status versus browsing all, or point explicitly at proposal_submit as the write alternative, so no exclusions are covered.

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