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

The description adds substantial behavioral context beyond the readOnly/idempotent annotations: it never guesses scores, never turns uncovered names green, and clarifies that the SHA-256 is not attestation or proof of publication time. This is valuable disclosure of limitations and semantics.

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?

The description is compact yet information-dense. Three sentences cover purpose, input constraints, output contents, and critical caveats without redundancy. Every sentence contributes unique meaning.

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 tool with a single parameter and no output schema, the description tells the agent what the packet contains (canonical values, URLs, lens bases, hashes) and warns about the hash's limitations. This is sufficient for correct invocation and expectation setting.

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?

The schema only says 'exact Failure Radar slug or full institution name.' The description adds 'or one unique case/punctuation-normalized full name' and explicitly states 'never fuzzy-matches,' giving the agent precise guidance on acceptable input forms and rejection behavior.

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: 'Build the compact human-review handoff for one fresh-vetted Indian Failure Radar institution.' It clearly distinguishes this from siblings by specifying the India scope and the exact-match-only behavior, contrasting with search/evidence tools.

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?

It states when to use the tool (for a fresh-vetted Indian institution with an exact slug/name) and explicitly says 'never fuzzy-matches,' implying you must already know the exact identifier. It does not name alternative tools but gives strong contextual boundaries.

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