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

Annotations only declare readOnlyHint=true, and the description goes meaningfully beyond that by disclosing the conditional behavior (SQL is returned only when the proposal is approved) and by naming the two artifacts (up and down) produced per engine. It still doesn't describe the possible status values or what happens for a nonexistent proposal id.

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?

Three short sentences, front-loaded with the primary return value, then the conditional payload, then the actionable instruction. No sentence is filler and nothing is buried.

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 must carry the return-value burden, and it covers the approved case well (up/down SQL per engine). It leaves the shape of the non-approved status response and error behavior for unknown ids unspecified, which is a modest gap for a two-parameter read 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 only 50% (proposal_id is undocumented), so the description must compensate, and it does partly by tying the "chosen engine" to the SQL dialect that is returned. That adds real meaning beyond the schema's generic "Database engine" note, though proposal_id's semantics remain undocumented in both places.

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 names a specific verb and resource ("Returns a proposal's status") and adds the conditional payload of up/down migration SQL, so the agent knows exactly what comes back. It never explicitly contrasts itself with list_proposals or propose_change, so the differentiation is inferable from the name rather than stated.

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?

Usage is only implied: the agent can infer this is the polling step after propose_change, and the closing instruction tells it what to do with the returned SQL. There is no explicit when-to-use or when-not-to-use guidance, and no mention of how it differs from list_proposals for status checks.

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