edit_message

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

The readOnlyHint=false annotation already signals mutation, so the description's job is to add context, and it does: it discloses a destructive nuance that 'files (replaces the attachments when given)' overwrites existing attachments rather than appending. It still leaves open what happens to omitted fields (whether embeds/link_buttons are preserved or cleared) and whether editing a non-bot message errors out.

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?

A single sentence with the verb and target front-loaded, the editable surfaces grouped, and the one dangerous caveat placed in a trailing parenthetical. Nothing is padding and nothing critical is buried.

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 10-parameter mutation tool with no output schema, the description covers the core content fields and the attachment-replacement hazard, which is the most important thing an agent could get wrong. It stops short of describing merge-vs-overwrite semantics for the other array fields and never mentions dry_run, which is the tool's own safety valve.

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 50%, so half the parameters rely on the schema alone. The description adds genuine meaning for files (replace-not-append) and identifies the four content categories, but says nothing about bot, server, channel, dry_run, or suppress_embeds, leaving a meaningful share of parameters uncontextualized.

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 gives a specific verb ('Edit') plus resource ('a message') and narrows the scope to messages 'the bot sent', which separates it from read paths like get_message. It also enumerates the editable surfaces (text, embeds, link buttons, files). It never names send_message as the creation counterpart, so the differentiation is strong but not explicitly routed.

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 'the bot sent' qualifier implicitly tells the agent this is not for editing other users' messages, which is a real usage constraint. There is no explicit when-not guidance, no mention of alternatives such as send_message for new messages, and no stated preconditions (existing message id, permissions).

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