add_pending_row

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

Annotations (readOnlyHint=false, destructiveHint=false) indicate mutability but non-destructiveness. The description adds nuance: 'source Excel is NOT modified' and 'fully reversible before approving the full run', clarifying the session-level mutability. This extra context is valuable and consistent with annotations.

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?

The description is extremely concise (4 sentences) with front-loaded action statement. Each sentence adds essential context: purpose, in-memory behavior, reversibility, and cost update. No superfluous words.

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?

Given the tool's complexity (4 parameters, output schema exists), the description fully covers behavioral context: non-modification, session storage, reversibility, and cost impact. The agent can understand the tool's role and side effects without needing additional explanation.

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?

Input schema covers all 4 parameters with descriptions (100% coverage). The description does not elaborate on parameters beyond the schema, but baseline is 3 due to schema coverage. No additional semantic value is provided by the description.

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 clearly specifies the action ('Add a new entity as a pending row') and the context ('to be included in the full validation run'). This distinguishes it from siblings like 'add_validated_rows' (adds pre-validated rows) and 'include_row' (re-includes excluded rows), providing a unique purpose.

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?

The description explains the tool's behavior (no modification to source Excel, stored in session state, reversible before approval) which gives clear context for when to use it. It implicitly advises against using it for permanent modifications, though it lacks explicit 'do not use when' guidance or direct sibling comparison.

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