Scoring Configuration

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

Annotations already provide idempotentHint=true and non-destructive. The description adds valuable context: updates are partial (patch-style), and changes do not affect previously scored leads until re-scored. This goes beyond annotations to explain the temporal scope of mutations.

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 a single compact paragraph of four sentences. It front-loads the primary verb ('View or update'), covers both usage modes, and lists parameter groups without redundancy. Could potentially be split into bullet points for better scanability, but it is sufficiently concise.

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?

For a read/write configuration tool with no output schema, the description should describe the return value format. It mentions 'fetch the current config' but does not specify the structure of the response (e.g., that it mirrors the input schema fields). Additionally, no mention of error handling, authentication, or rate limits. Given the complexity (10 parameters, nested custom_rules), the output format is a meaningful gap.

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 has 100% description coverage, so baseline is 3. The description adds default values (e.g., 'Default 0.25' for job_title_weight), explains constraints ('each 0–1, should sum to ~1 but not enforced'), and clarifies behavior like 'replaces the existing rule list when provided' for custom_rules. This adds significant context beyond the schema.

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 states the dual purpose: 'View or update the global lead scoring configuration.' It specifies the exact verb-resource pair and distinguishes from sibling tools like `lead_score` by noting that the config applies to future calls only.

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 instructs when to fetch ('call with no fields') and when to update ('pass any subset of fields'). It also clarifies scope ('Changes apply to future lead_score calls only') and sets expectations about previously scored leads. However, it does not explicitly list sibling tools to avoid or conditions under which to avoid using this tool.

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