source_text

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely behavioral fact – that supplying grep narrows output to matches with surrounding context – but says nothing about truncation, size limits, or what happens when ref is unknown.

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 core definition is front-loaded in the first sentence and the citation instructions are actionable rather than filler. The second half is process guidance rather than tool description, but it earns its place by constraining how results should be reproduced.

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 does reasonably well at describing the shape of the return value (visible text, or only grep matches with context). For a four-parameter read tool it leaves too much unexplained – notably store, context, and any limits – to be considered fully complete.

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 description coverage is 0% with four parameters, so the description bears the full burden. It does explain ref (URL or sha256 prefix) and how grep alters output, but 'store' and 'context' (including its default of 160) are never mentioned anywhere, leaving half the parameter surface undocumented.

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 resource (the visible text of a snapshot) and clarifies the ref format as URL or sha256 prefix, so an agent knows exactly what comes back. It does not, however, differentiate itself from siblings like summary or snap, so the agent must infer when this is the right source of text.

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 through the citation workflow – copy quotes character for character, wrap in quotation marks, and link the snapshot URL in the same sentence. There is no explicit statement of when to pick this over summary or verify_report, and no preconditions are named.

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