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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses significant behavioral traits: it opens an interactive viewer, shows transcription text alongside, supports optional highlighting, and falls back to a text summary plus inline preview images on hosts without MCP Apps support. This is rich, environment-dependent context not captured by annotations.

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 three sentences, each earning its place: the first states the primary function, the second explains input format and provenance, the third covers optional highlight and fallback behavior. No redundancy or fluff.

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 read-only viewing tool with two well-documented parameters and no output schema, the description fully covers what the tool does, how to obtain valid inputs, what the user sees, and how it behaves in different host environments. It is self-sufficient for an agent to select and invoke correctly.

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 baseline is 3. The description adds meaning by defining the exact identifier format ('<ISIL>_<archive>_<page>' with example) and stating that identifiers come from search_transcriptions / browse_transcriptions, which helps the agent construct valid input beyond the schema's generic 'array of strings'.

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 states the specific action ('Open') and resource ('transcribed document pages in an interactive deep-zoom viewer'), and distinguishes from siblings by mentioning the deep-zoom context and the source of identifiers from search/browse. It also notes the optional highlight feature and fallback behavior, covering scope fully.

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 explicitly tells the agent to pass page identifiers returned by search_transcriptions / browse_transcriptions, giving clear workflow context and input provenance. It also describes the fallback for hosts without MCP Apps support, which helps set expectations. It lacks explicit 'when not to use' exclusions, but the context is strongly indicative.

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