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

Annotations already cover read-only/idempotent/open-world, yet the description adds behavior they cannot express: search is literal substring only, not semantic; results are untrusted data; and classification rules silently exclude test topics unless overridden. These are exactly the traits an agent would otherwise get wrong.

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?

Four terse sentences, front-loaded with scope and immediately followed by the exclusion and the trust caveat. Dense but appropriately sized for a 7-parameter search tool; no sentence is filler.

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?

No output schema exists, so return format is undefined, but the description covers scope, exclusions, trust level, and matching semantics for a read-only search. Pagination and result shape are the only remaining gaps and are partly implied by the schema defaults.

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?

With only 43% schema coverage, the description must carry weight, and it does add real meaning: q is literal and case-insensitive, and the orbit/include_test interaction determines whether classified records appear. It leaves tag, kind, page, and per_page to the schema, but those are self-evident or enum-constrained.

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 and resource (search legacy memory records) plus the exact matching surface (literal keyword substring, orbit slug, kind, tag). It explicitly distinguishes itself from the sibling search_contributions, so an agent can route without opening either schema.

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?

Gives both when-to-use and when-not-to-use: 'Does not search revisioned contributions or task attempts; use search_contributions for the commons.' It also states the condition under which excluded test topics appear (include_test=true vs. explicit orbit slug), which prevents a class of mis-invocation.

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