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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description adds value beyond that by disclosing the external side effect ('who gets a push'), which is exactly the kind of real-world consequence an agent needs. It still omits delivery failure behavior, rate limits, or whether messages can be recalled.

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?

Two short sentences, front-loaded with the action and effect, then the confirmation constraint. No wasted words, though the second sentence is phrased as an instruction to the agent rather than as tool behavior, which is slightly ambiguous in register.

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-parameter, non-destructive send tool with no output schema, the definition covers what it does, who receives it, the push side effect, and the confirmation protocol. Only minor gaps remain around failure modes and whether a message identifier is returned.

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% – both content (up to 5000 characters) and receiver_id (student_id from list_students) are documented in the schema. The description only reinforces 'to a student' and adds no format or syntax detail beyond the schema, so baseline 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 recipient ('Sends a chat message to a student'), which clearly distinguishes it from read-only siblings like read_chat and list_conversations. It does not explicitly name the lead-facing alternative (reply_to_lead), so differentiation is implied rather than stated.

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?

The sentence 'Show the text to the person before sending' gives a genuine pre-send confirmation workflow, which is useful operational guidance. However, there is no explicit when-to-use vs. when-not guidance, and no routing to reply_to_lead or other messaging tools for different recipient types.

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