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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, but the description adds the reason: it consumes a credit ('Uses one read') and persists state ('saves the result in the user's Puley history'), which explains why a link-checking operation is not read-only. It also discloses that pages are fetched live at call time and enumerates every failure mode, so the agent knows what partial success looks like.

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 core action and the status taxonomy, then the optional parameter and use cases. It is dense with parentheticals and reads as a run-on, but every clause carries information (outcome states, limit, credit cost, history write) 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?

There is no output schema, and the description compensates by defining the return vocabulary (Live/Dead/Site doesn't exist/Site error/Exists but blocks readers/Couldn't confirm) and what Live includes (real title, redirect target). Combined with the credit cost and 15-link cap, an agent has enough to call this correctly and interpret the response without further documentation.

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 0%, so the description must carry parameter meaning and largely does: 'claim' is defined as what the pages should say, with the matching behavior spelled out ('each live page is checked for its main words'), and 'links' is bounded ('Up to 15 links'). Minor gap: it doesn't say whether claim matching is exact, keyword-based, or how mismatches are reported in the result.

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 resource ('Check whether links are real and live') and enumerates the exact outcome states (Live with title and redirect, Dead, Site doesn't exist, Site error, Exists but blocks readers, Couldn't confirm). This is clearly distinguishable from siblings like check_backlinks, check_site, read_site, or is_it_real, since it operates on a list of URLs rather than a site or claim.

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 concrete usage contexts ('Suits sources, citations, store or product links and recommended websites') plus the decision prompt '(is the site still up?)'. It also states the hard limit 'Up to 15 links'. It stops short of naming explicit alternatives (e.g., use check_site for a whole domain, check_backlinks for link equity), so the agent must infer exclusion boundaries.

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