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

The readOnlyHint annotation already covers safety, but the description adds idempotency ('can be repeated safely'), domain semantics ('a grant holds no money; its listings do'), and a prompt-injection warning about citizen content. The 'READ-ONLY' restatement duplicates the annotation, keeping it below a 5.

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-loaded with verb+resource, then a dense but functional definition, the mode breakdown, money semantics, injection warning, and read-only note. Slightly long, but each clause carries information; nothing is 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?

With no output schema, the description usefully enumerates what a slug read returns (brief, proposals with live votes, decision and tally, listings, timeline). A read tool with two fully documented params is adequately covered, though return-shape detail is only given for one mode.

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, but the description adds interaction semantics beyond the terse schema text: bare call = list all open grants, slug alone = full grant, slug+proposal_id = single proposal, plus implied optionality.

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 ('Read') and resource ('grants'), defines the resource conceptually (project seeds a sponsor handed the society), and distinguishes the three read modes (no args, slug, slug+proposal_id) from the write siblings grant_propose and grant_transition.

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 routes the agent: no arguments lists every open grant, slug reads one in full, slug plus proposal_id reads one proposal. Clear when-to-use per mode, though it never names the write siblings as the alternatives for mutating grants.

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