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

Annotations already declare readOnly=false, destructive=true, idempotent=true and openWorld, so the safety profile is covered. The description adds genuinely useful beyond-schema behavior: 'Omitted fields stay; null clears', which tells the agent how to avoid wiping a title accidentally — a real destructive-risk disclosure. It stops short of saying what is returned, whether the change is immediately live, or what happens with an unknown slug.

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 dense sentence with the scope constraint front-loaded and the destructive-clear rule trailing; every clause carries information. The parenthetical '(not the page's own HTML)' and the semicolon-joined clearing rule are both load-bearing rather than filler.

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 four-parameter metadata setter with annotations covering safety and idempotency, the description supplies the two things annotations cannot: which surfaces the change affects and how null/omission behave. With no output schema present, a note on the response or on validation failure (unknown slug) would be the only 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 0%, so the description carries the burden and it does cover the most dangerous semantics — omission preserves, null clears — plus the meaning of searchIndexing ('whether search engines may list it'). Title and description are named as the fields being changed, though maxLength limits live only in the schema. The required 'slug' parameter is never explained as the site identifier, leaving one of four parameters undocumented.

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 ('Change the title and description ... for a site') and names the exact downstream surfaces affected (dashboard, profile project cards) while excluding the page's own HTML. That exclusion is a real disambiguation against content-editing tools. It does not, however, distinguish itself from close siblings like update_site, edit_site, or rename_site.

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?

Usage is implied rather than stated: an agent can infer 'use this when you want to change site metadata but not page content'. There is no explicit when-to-use/when-not and no pointer to the apparently overlapping siblings update_site or edit_site, so routing between them still requires guessing.

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