db_dry_run

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses that execution happens inside an auto-rollback sandbox (no persistent writes), that blast radius and row counts are computed, and that a short-lived token is issued conditionally. The notable gap is the 'if safe' branch — the description never says what happens when the mutation is deemed unsafe (error, refusal, null token) or how long the token lives.

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 sentences, both information-dense, with the core behavior (simulation in a rollback sandbox) front-loaded before the outputs. No filler or restatement of the tool name.

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 usefully enumerates the return payload (blast radius, row count, token). For a mutation-adjacent tool with zero annotations, the missing piece is the failure/unsafe path and the token's downstream contract with db_commit.

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%, so the schema already documents sql, intent, and params including the accepted mutation types. The description adds no further meaning about parameter usage, such as whether parameterized values in params are required for safe blast-radius estimation or how intent influences the safety decision.

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 — simulate a database mutation — and scopes it to an auto-rollback transaction sandbox, then adds what it computes (blast radius, affected row count) and what it emits (a short-lived authorization token). This clearly separates it from db_commit (which would apply changes) and db_query (which reads), though no sibling is named explicitly.

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 word 'simulate' and the token return suggest this is a pre-flight step before db_commit. There is no explicit when-to-use or when-not statement, no mention that db_commit presumably requires the returned token, and no exclusion telling the agent to use db_query for read-only SQL or db_explain_query for plan inspection.

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