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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered externally. The description adds that deletion is targeted at primary keys, which tells the agent the operation is precise rather than bulk/pattern-based, but it says nothing about batch atomicity (up to 100 identities), behavior on missing rows, or failure semantics. Given the annotation coverage, a 3 is appropriate.

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 short sentences with the core action and targeting mechanism front-loaded; nothing is padded or buried. The second sentence is marginally redundant with the schema's identities description, keeping it just below top marks.

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 an output schema present and rich annotations, the description does not need to explain return values or safety hints. However, for a destructive batch-delete it omits relevant context: whether deletes are all-or-nothing across the identities list, how missing keys are handled, and any confirmation requirements, leaving the agent to guess at failure behavior.

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 table, schema, project_id, and identities are already documented in the input schema. The one added clarification — that 'identities is a list of key objects' — largely restates the schema's 'Primary keys of the rows to delete' and does not explain the expected key-object shape. Baseline 3 applies when the schema does the heavy lifting.

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 gives a specific verb and resource ('Delete Cloud Postgres rows') plus the targeting mechanism ('by primary key'), which clearly separates it from siblings like projects_cloud_database_row_update, projects_cloud_database_row_insert, and projects_cloud_database_rows. It stops short of naming those siblings explicitly, so it lands at 4 rather than 5.

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?

There is no guidance on when to use this tool versus the query/insert/update siblings, no prerequisites (e.g., rows must exist, project ownership), and no warnings about the destructive nature of the call. The only implicit usage signal is 'by primary key', which tells the agent what input is required but not when to choose this tool.

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