why

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

With no annotations, the description carries the full burden, and it does disclose the shape of the result set (reasons, evidence, rejected alternatives, outcomes, supersession chain), which is genuinely useful behavioral detail. It does not say the tool is read-only, whether the search spans all stored decisions or a scoped subset, or what happens when nothing 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 sentence, front-loaded with the motivating question form before the enumeration of returned components. Every clause contributes and nothing is padded, though the example-question framing costs a few tokens before the substance arrives.

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 one-parameter read tool with no output schema, the description adequately conveys return contents but leaves scope, safety profile, and matching behavior unstated. Nothing is dangerously missing, but an agent cannot fully predict the tool's boundaries from the definition alone.

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 0% for the single required 'topic' parameter, so the description must compensate. The phrase 'matching the topic' adds meaningful semantics — it implies matching rather than exact identifier lookup — but does not clarify whether topic is a keyword, a phrase, or a full natural-language question, nor how matching is performed.

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 retrieval: full decision chains for a given topic, enumerated as reasons, evidence, rejected alternatives, outcomes, and supersession. That is more than a restatement of the name 'why' and tells an agent what comes back. It stops short of explicitly contrasting itself with siblings like recall, timeline, or current_fact, so 4 rather than 5.

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?

The quoted example question 'why did we choose X?' implies the use case — historical rationale retrieval — but the definition never states when not to use it or which sibling to prefer for facts, chronology, or conflicts. An agent can infer usage from the example, but routing between why and recall/timeline is left to guesswork.

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