mediawiki_audit

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

Annotations already declare readOnlyHint, openWorldHint and idempotentHint=false, so safety and mutability are covered. The description adds two genuinely useful behavioral notes: that the 'external' check is slow, and that the response contains a health score plus per-check results and recommendations. It undercuts itself with inaccurate defaults ('default all' vs. the schema's 'all except external', and 'max items per check' vs. the schema's 'max pages to audit'), and never explains the non-idempotent behaviour the annotation flags.

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 one-line purpose, then cleanly sectioned into USE WHEN / PARAMETERS / RETURNS, and every line is scannable. Some redundancy with the schema (restating checks and limit) and a couple of imprecise sentences keep it from a 5.

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?

With an output schema present, the RETURNS line is a bonus rather than a requirement, and the trigger phrases and check list are adequate. The notable gap is scoping: 'pages' and 'category' let an agent audit a subset, yet the description never mentions either, so an agent may launch a full-wiki audit when a targeted one was intended.

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 the baseline is 3 and the schema carries the detail for all five parameters. The description enumerates the meaning of each check value (a helpful gloss on an enum-less string array) but mischaracterizes 'limit' as items-per-check rather than pages-to-audit, omits the 'max 50' cap, and says nothing about 'pages', 'category' or 'rationale'.

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 ('Run comprehensive wiki health audit') plus the multi-check scope, so the aggregate nature of the tool is clear. It does not, however, explicitly differentiate itself from the many single-check siblings (mediawiki_check_links, mediawiki_check_terminology, mediawiki_find_broken_internal_links, mediawiki_find_orphaned_pages), which is precisely the distinction an agent needs.

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 'USE WHEN' section gives three concrete user phrasings ('run health check', 'audit the wiki', 'check wiki quality') that map cleanly to invocation contexts. It stops short of naming alternatives or exclusions, e.g. 'for a single check, call mediawiki_check_links instead', which would make routing between this tool and the per-check siblings unambiguous.

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