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

Annotations already declare readOnly, idempotent, open-world and non-destructive, and the description still adds substantive behavior the annotations cannot express: a $0.01 per-call cost, the 100k character ceiling, SHA-256 provenance in the payload, the rejected host/scheme/URL/size/timeout classes, and the fact that failures surface explicit upstream status. That is unusually rich disclosure for a read tool.

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-loads the decisive cost-and-default signal ('DEFAULT ($0.01/call)'), then purpose, then limits and failure modes in three dense, waste-free sentences. Nothing is padded and the most decision-relevant fact comes first.

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, the description correctly carries the return contract (size cap, metadata, timestamp, provenance) and covers cost and error behavior, so an agent can call it correctly. The one omission is any statement of how it relates to gridextract_markdown or gridverify_evidence, leaving an overlap unresolved.

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?

There is a single parameter and the schema already documents it at 100% coverage, including the same private-host and nonstandard-port rejection rule the description repeats. The description adds little beyond the schema for this parameter, so the baseline of 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?

States a specific verb and resource ('Fetch fresh content from one public HTTP/HTTPS URL') plus the payload returned ('up to 100k characters of machine-ready text with source metadata, timestamp and SHA-256 provenance'). An agent can tell it is a general web-retrieval tool, but the description never contrasts itself with the sibling gridextract_markdown, which plausibly overlaps, so it stops short of a 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?

'Use for web retrieval when you need current source content' gives explicit context for when to reach for this tool, and the rejection list sketches its boundaries. It offers no when-not guidance and names no alternative tool, so the agent gets context but no routing rule between it and its siblings.

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