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

With only readOnlyHint=true in annotations, the description adds substantial behavior: link lifetime (default 15 min, max 60, expires_at), the failure reason taxonomy (over 5MB, deleted, external, no permission), the fact that links work without signing in, and a security constraint against reposting them. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with the primary action and scope, then layered constraints; every clause carries information. Slightly dense with nested parentheticals, but no filler or repetition.

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?

No output schema exists, yet the description fully describes the return shape (name, mime type, size, download_url or a reason code) plus the expiry semantics and revocation path. Nothing an agent needs to call and interpret this tool is missing.

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%, so ts/message/channel/thread_ts/ttl_minutes are already documented upstream; the description only re-states that no file ids are needed and echoes the 15-minute default. That is baseline behavior when the schema does the heavy lifting.

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+resource+scope: 'Read ONE Slack message (its text) and get a download link for EVERY file attached to it'. The emphasis on 'no file ids needed' and 'ONE' cleanly separates it from read_slack_file/read_file_content (single-file content reads) and list_slack_files.

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 clear downstream usage rules (hand links to the user, never post elsewhere, revoke early with revoke_slack_file_links) and implies the boundary with content-reading tools via 'Files are NOT read, converted or analysed'. It does not, however, explicitly name the alternative tool to use when the agent actually wants file contents.

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