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

Annotations indicate destructiveHint=true and readOnlyHint=false, which the description complements by detailing side effects: impact_only=false rewrites aliases, entity identities, referencing payloads, and queues convergence. It also discloses 'No LLM call' and warns that similarity alone does not establish identity, adding important behavioral context beyond the structured 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 compact and well-structured: it opens with the core action, then explains default behavior, conditional behavior, prerequisites, and output. Every sentence contributes essential information with no redundancy, making it easy for an agent to parse quickly.

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 destructive, two-phase operation, the description covers all necessary aspects: default safety mode, owner requirement, consequences (alias/identity rewrites, convergence queueing), non-LLM nature, prerequisite evidence checks, and output type. It references documentation and related tools, ensuring an agent has enough context to invoke it correctly.

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 all three parameters. The description adds value by elaborating on impact_only's dual semantics (impact reporting vs. actual merge with owner requirement) and the consequences of each mode, going beyond the schema's brief descriptions. It doesn't add new info for winner_id/loser_id, but the mode explanation justifies a score above baseline.

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 action: 'Merge a loser concept into a winner.' It distinguishes two operational modes (impact_only true/false) and explicitly notes that similarity alone is insufficient, implying this is an identity-based merge rather than a fuzzy match. This separates it from sibling tools like merge_records or update_concept_alias.

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?

It provides explicit when-to-use guidance: defaults to impact_only=true for inspecting counts and affected replicas before approval, while impact_only=false requires owner role. It also advises inspecting get_semantic_concept and judge review evidence first, and points to enricher://docs/semantic-ids for further details. No ambiguity about prerequisites or modes.

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