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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: results are compact and intended to keep context window and cost low, and it is a precursor to a narrower follow-up call. It does not discuss result volume or the limit cap, which the schema handles.

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, zero waste. The content of the return is front-loaded and the workflow instruction plus its rationale follow immediately. No repetition of schema or annotation material.

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 and 7 parameters, the description must convey return shape, and it only names content categories (negotiations, learnings, verified runs) without structure or size expectations. The workflow guidance is complete, but an agent still cannot predict whether it receives prose, ranked lists, or records.

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 100%, so query, intent, limit, and context are already documented in structured data. The description reinforces the query semantics ('most relevant verified script') and ties the recall intent to generate/repair workflows, but adds no syntax or filtering detail beyond the schema. Baseline 3 applies.

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?

Specific verb-plus-resource: returns 'compact durable memory' scoped to prior agent negotiations, project learnings, and verified test runs. It also signals its boundary against the sibling get_script, so an agent can distinguish recall from script retrieval without opening a schema. The wording 'durable memory' is slightly abstract, but the enumerated sources anchor it.

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?

Explicit sequencing: 'Call this before generating or repairing tests for an existing project; then call get_script only for the most relevant verified script.' It names the alternative and the reason (cost/context), which is strong guidance. It stops short of explicit exclusions (e.g., no memory for a brand-new project), so not a 5.

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