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

Annotations already declare readOnly/destructive=false, but the description adds what the annotations cannot: it returns sha256 and draft_version (so it supports optimistic concurrency checks), it names the key scope deploy:write, and it discloses the 415 binary_file failure mode. That is substantive behavior beyond structured fields.

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?

Three short sentences, front-loaded with the read-only trait, then the return payload, then the workflow rule and the binary edge case. 'A picture answers 415 binary_file.' is terse to the point of being slightly cryptic, but nothing is wasted.

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 two-param read with no output schema, the description still discloses the two return fields, the permission scope, and the binary failure case. It stops short of stating what happens when the path does not exist in the draft (404/empty), which is the one remaining gap.

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 100% — both 'site' and 'path' already carry their own documentation including the path example format. The description adds no further parameter detail, 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?

Names a specific verb and resource ('One text file of the draft … as it is now') and scopes it to text formats with examples (HTML, CSS, SVG, JSON). It also names the sibling write_files as the contrasting operation, so an agent can separate it from get_draft or get_schema without opening a schema.

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?

Gives an explicit when-to-use rule: 'Use it before write_files when you change a page: write_files replaces whole files.' That single clause names the read-before-write workflow and the alternative tool, and the 415 note covers the case where the path is a binary asset instead.

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