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

Goes well past the readOnly/destructive/openWorld annotations: it discloses the k=3 anonymization floor with "never who", per-UTC-day quotas by plan tier (Free 5, Spark 50, Growth 500, Studio unlimited), how `remaining` behaves, and that a 402 response carries upgrade links. It also states the required read scope, which an agent needs before calling.

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?

Front-loaded with the core action, and the quota/error sentence earns its space by preventing wasted calls. The middle clause is a dense run-on with nested parentheses that takes effort to parse, costing it the top score.

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?

An output schema exists, so return values need not be restated, and the description still covers auth scope, quotas, and error signaling. The remaining hole is sibling disambiguation against reference_search/references_list, which matters given how crowded that namespace is.

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 100%, so the baseline is 3, but the description adds real semantics: q is described as a handle, partial handle, or name, and crucially platform combined with an exact handle changes the result shape to co-pick analysis — meaning the schema's bland "Narrow to one platform id" understates. Only `limit` is left to the schema.

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 opens with a specific verb+resource ("Search the reference graph") and enumerates the three distinct result modes it can produce. It never distinguishes itself from the similarly named siblings reference_search, references_list, or reference_read, so an agent cannot tell from the text alone which of those to pick.

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?

Usage is implied rather than stated: the agent can infer that supplying platform plus an exact handle unlocks the co-pick view, and that omitting them yields match/count modes. There is no explicit when-to-use, when-not, or naming of reference_search/references_list as the alternatives for plain lookups.

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