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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely non-obvious behavior: rows are keyed by localized option names in the GLPI user's language, coded columns appear as '<name> (id)', and named_columns=false switches to numeric option IDs. This is real disclosure beyond the structured fields.

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 but front-loaded: purpose first, then criteria grammar, then output-keying semantics, then the pointer to glpi_list_search_options. Every clause carries information, though the single-paragraph block is heavy for one read.

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?

Given a rich 9-param schema, an output schema, and annotations covering safety, the description fills the remaining gaps: criteria grammar, localized/raw keying modes, and the search-option discovery dependency. An agent has enough to call this correctly.

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% for the top-level params, but the criteria items are only 'additionalProperties: {}'. The description compensates by defining the criterion shape ({field, searchtype, value, link}), enumerating legal searchtype values (contains | equals | notequals | lessthan | morethan | under), link semantics (AND | OR, omit on first), and the group form {link, criteria: [...]}.

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 (search) and resource (GLPI items) and enumerates valid itemtypes (Ticket, User, Change, Problem, Computer). It implies but never explicitly distinguishes itself from the many specialized glpi_list_* siblings, so the agent must infer that criteria-based search is the differentiator.

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 one concrete prerequisite-style tip: use glpi_list_search_options to discover option IDs for criteria, forcedisplay and sort. However, it never states when to prefer this generic search over glpi_list_tickets, glpi_list_users, or glpi_count_items, leaving tool selection to inference.

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