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

Annotations only declare readOnlyHint and openWorldHint, so the description adds the real behavioral context: Spanish stemming dictionary, relevance ordering, default limit of 25, credential-derived default workspace, and notably that identifier searches without workspaceId span all workspaces and may return duplicates across rows. That cross-workspace side effect is exactly the kind of trait an agent cannot get from 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?

Front-loaded with what the tool does and what it returns, then progressively more specific parameter rules, with no filler sentences. It is dense and long, and the trailing explanation of why identifiers are not unique across workspaces restates at more length than needed.

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?

Four parameters, no output schema, and the description still documents the return shape (issue fields, snippet with <mark> tags, rank, embedded customFields so no per-issue fetch is needed), which removes the need for an output schema. Nothing an agent needs in order to call it correctly appears to be missing.

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?

With 0% schema description coverage the description carries the full burden, and it does: query (full-text or exact TEAM-N), limit (1-100, default 25), workspaceId (default from credential; list_workspaces enumerates), and customFields with the {fieldId, op, value, value2} shape plus per-type operator sets and value formats (userId for member, epoch ms for date, value2 for between, AND-combination with query). Minor caveat: its stated limit range of 1-100 is stricter than the schema's integer bounds, a small inconsistency worth noting.

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 ('Busca issues por FULL-TEXT') and pins down the exact mechanism (Postgres tsvector, diccionario español, ts_rank) plus what each result carries, which is far more than the name conveys. It never names the sibling it competes with, however: the note 'query vacía + customFields = listado filtrado' effectively overlaps list_issues without telling the agent which to prefer.

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 explicit conditional guidance inside the tool: full-text via query, narrowing via customFields, empty query + customFields as a filtered listing, and exact-identifier lookup. It also explains the cross-workspace consequence of searching a TEAM-N without workspaceId. It stops short of stating when NOT to use it (e.g., retrieving a single issue by id, or browsing with list_issues).

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