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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds context they cannot: the response includes the endpoint-specific call form, and coverage is limited because 'unknown, administrator and hidden compatibility tools are not listed.' The 'does not execute or grant permission' line partly restates destructiveHint=false, but the visibility limitation is genuine added information.

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?

Four short sentences, each doing distinct work: purpose, parameter scope, sourcing/preconditions, and coverage limits. The core purpose is front-loaded and nothing is padded.

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 sketches the return ('input schema and endpoint-specific call'), and both parameters are addressed. What remains unstated is failure behavior for an unknown or admin-restricted tool name and the omitted-operation case, which matters given the explicit note that some tools are not listed.

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%, so the description must carry both parameters, and it largely does: 'tool' is sourced from 'a name from a next step' and 'operation' is explained as selecting one branch of a multi-operation tool. The gaps are minor but real — it does not say what is returned when operation is omitted, nor how a branch name is discovered.

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 — 'Get the current input schema and endpoint-specific call for one named Speedbot tool' — and immediately scopes it to a single named tool rather than a listing. The closing sentence ('this does not search work, execute the target or grant permission') separates it from the action/execution siblings in the same family. An agent can tell what this returns without opening the 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 a real precondition for use ('Use a name from a next step') and an explicit exclusion (it does not execute the target or grant permission), which is the main confusion risk in a large sibling set. It also flags when to add the operation parameter. It stops short of naming an alternative sibling such as speedbot_read_tool for discovery, so it is not a full when/when-not/alternative statement.

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