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

Annotations only say it is a non-read-only, idempotent, non-destructive, open-world call; the description adds the substantive behavior: a visible editing mark shown to humans, a ten-minute expiry measured from the last write, and hard refusal of this and every write while a person has the post open. It also forbids circumventing the refusal, which is exactly the kind of behavioral constraint structured fields cannot express.

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?

Dense and almost every sentence carries operational weight — expiry, refusal handling, and the handoff to finish_editing_post. The leading sentence fragment is malformed and delays the point, and the guidance is front-loaded only after that fragment, but there is no filler prose.

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 coordination tool with no output schema, the definition covers the important ground: when to call, what the mark means, how long it lasts, what refusal looks like and what to do about it. The only gap is that it never says what a successful call returns (e.g., confirmation or mark metadata), which matters slightly since there is no output schema to fall back on.

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%, so both parameters are already documented (site per list_sites, post_id per list_posts), and the description largely restates that site is named in the site parameter. The one genuine addition is that the target may be "a post or a page," hinting post_id may cover pages — useful, but the schema still calls it post_id from list_posts, leaving that ambiguity unresolved.

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 conveys that this registers/announces an editing session on a post before changes are made ("It tells the people who open the post in the editor that you are writing it"), and it clearly distinguishes itself from edit_post (call this first) and finish_editing_post (call when done). The opening fragment "On one site of the account, named in site" is grammatical debris rather than a purpose statement, so the core action (acquiring an editing mark/lock) is inferred rather than named directly.

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?

Explicit sequencing ("Call this first, before you plan a change to a post or a page"), an explicit counterpart ("Call finish_editing_post when you are done"), and an explicit failure path: if refused, tell the asking person and "do not write the post another way." Both when-to-use and how-to-behave-under-conflict are spelled out with nothing left to inference.

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