memory_pattern_predict

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the 'never execute it or grant access' clause largely restates that rather than adding new information. Beyond that, the description leaves open what an 'exact-match locally verified' script means, and what the tool returns when no pattern matches.

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?

A single front-loaded sentence with no filler and the key constraint stated early. It is efficient, though the terseness borders on under-specification handled under other dimensions.

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, three required inputs including a nested object, and one of the more conceptually opaque tool names in the set, the description should explain the matching contract and return shape. It instead gives one constraint sentence, leaving an agent unable to predict what happens for a partial or no-match case.

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 0% and all three required parameters — project_root, task_type, and a nested free-form 'features' object — are undocumented in both the schema and the description. The phrase 'exact-match' faintly hints that matching keys off the supplied inputs, but the description never explains what belongs in features or how task_type is used.

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 the output ('an exact-match locally verified script reference'), which tells an agent what it receives, but the verb is 'suggest only' rather than a clear prediction action, and 'pattern predict' from the name is never explained. It also does nothing to separate this from siblings like memory_recall or memory_engineering_context, which likely also surface stored artifacts.

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?

There is no when-to-use guidance — nothing says what kind of query, task, or state should trigger this tool versus the recall siblings. The only directive is a negative constraint ('never execute it or grant access'), which governs downstream handling of the result rather than tool selection.

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