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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuine value by disclosing the free-text query style and, importantly, the return contract ('Returns ids for `fetch`'), which is the key behavioral fact given there is no output schema.

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?

One tight sentence with the corpus named first, examples in parentheses, and the return contract last. Every clause carries information; no filler. It could be marginally cleaner, but nothing 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?

For a single-parameter read tool with no output schema, the description covers what is searched, how to phrase the query, and what comes back (ids for fetch) — the essentials. It omits ranking, result limits, or fallback behavior when no match is found, which is a minor 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?

Schema coverage is 100% and the single parameter is already described as 'Plain words or a purpose code.' The description goes beyond that by supplying three concrete example queries, giving the agent a real sense of the expected input shape (natural language phrases as well as code identifiers).

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 (search) and resource set (compliance guides plus the RBI purpose-code reference), so the agent knows exactly what corpus is queried. It does not explicitly distinguish itself from sibling find_purpose_codes or get_purpose_code, which also concern purpose codes, leaving some ambiguity about which to pick for a code-only lookup.

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?

Usage is implied through the free-text examples ('EDPMS entry not closed', 'Form 145 Part C') and the note that results are 'ids for fetch', which hints at a search-then-fetch flow. However, there is no explicit when-to-use versus when-not guidance and no mention of find_purpose_codes as the alternative for direct code lookups.

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