compute_multi_source_tam

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

There are no annotations, so the description carries the full behavioral transparency burden and does so thoroughly. It discloses return components, the hasStaleData flag semantics, the outlier-removal rule with modified Z-score/MAD at n≥4, and the exact meaning of an agreement score of 1. This gives the agent a strong model of what will happen.

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?

Every sentence contributes operational value: input count, optional parameter behavior, outlier handling, and return semantics. The purpose is front-loaded and there is no filler or repetition.

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?

The description covers outputs and algorithms unusually well, but it contains an internal inconsistency: it instructs the agent to pass 2-3 sources while also specifying outlier behavior when n≥4, which would be unreachable under that stated limit. It also omits behavior for fewer than 2 sources and does not clarify the `source` field's intended meaning, which could lead to incorrect invocation.

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 schema description coverage at 0%, the description compensates by explaining the input shape: 2-3 sources of market-size text, optional per-source estimateYear, and the downstream effect of supplying estimateYear. It could more explicitly describe the `source` and `text` fields, but their meaning is recoverable from context.

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 clearly identifies a specific operation: multi-source TAM consensus using market-size text. It distinguishes itself from the many sibling compute_* tools by naming TAM specifically and describing extraction, aggregation, and agreement scoring. This goes well beyond restating the tool name.

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 description tells the agent to pass 2-3 sources of market-size text and explains when the optional estimateYear is relevant. It does not name alternative tools or state explicit when-not-to-use conditions, but the usage context is clear enough to select this tool among its siblings.

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