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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile is fully covered and the description does not contradict it. The description adds a return-content inventory (definition, difficulty, questions to ask, synonyms, canonical_url), but since an output schema exists this mostly restates structured data rather than disclosing new behavior such as invalid-slug handling or caching.

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 sentences, front-loaded with the when-to-use condition followed by the return contract, with zero filler. The example list is dense but each item is a distinct, useful cue rather than redundant restatement.

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 single-parameter read-only lookup with a full output schema, the description covers the trigger, the input vocabulary, and the return shape adequately. The remaining gap is operational: it does not point the agent at list_specialties for discovery or describe the failure mode for an unrecognized slug, which matters given the tool's narrow closed-world scope.

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 100% and the slug property already enumerates all 36 accepted values, so the baseline is 3. The description earns an extra point by translating colloquial user phrasing ("bank statement loan", "ITIN loan", "non-warrantable condo") into slug-like terms, helping the agent map a natural-language question to the right slug, though it does not state casing or format expectations explicitly.

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 states a specific verb (explain) and resource (a mortgage specialty slug) and enumerates concrete examples of the domain objects (DSCR loan, bank statement loan, ITIN loan, non-warrantable condo, FHA loan). An agent can tell this is a lookup/explanation tool rather than a search or retrieval-by-id tool, though it never names its siblings (list_specialties, get_lender) to sharpen the distinction.

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?

"Use this when someone asks what a mortgage loan type or borrower situation means" gives a clear triggering condition with illustrative phrasings that match real user questions. It stops short of exclusions — it never says to call list_specialties first to discover valid slugs, nor what to do when the question spans multiple specialties.

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