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

Goes well past the annotations (which already declare read-only, idempotent, non-destructive, closed-world) by disclosing data handling ('processed remotely but not saved'), enumerating the inferences it refuses to make (missing ≠ wanted, no quantities, no trade intent, no completeness certification), and stating a storage boundary. For a no-output-schema tool it also describes the return set.

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?

Front-loads the core comparison in sentence one and the return set in sentence two, with constraints and the provenance rule after. The list of four 'does not' clauses is slightly dense but each clause prevents a plausible misreading, so little is wasted.

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 no output schema, the description correctly spends words on the return payload, and it covers privacy and the exact-name prerequisite. Minor gap: the seriesId parameter and the language enum's practical effect are only obliquely addressed.

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 coverage is 75%, so baseline is 3; the description earns an extra point by clarifying that names must be distinct and exact, that wanted names are only those explicitly supplied, and by implying seriesId comes from search_collection_series — a parameter the schema leaves undocumented.

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?

States a specific verb ('Compare') and both operands (user-supplied distinct owned names vs. one verified series), then enumerates exactly what comes back (owned, not-marked-owned, wanted, unmatched, Markdown checklist). This is clearly distinguishable from siblings such as estimate_collection_progress or search_collection_series.

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 names the prerequisite source for its inputs: 'Use exact names from search_collection_series,' which routes the agent across tools. It does not, however, contrast itself with related siblings like estimate_collection_progress, so the when-to-use vs. alternatives framing is implied rather than stated.

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