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

Annotations already declare readOnlyHint=true and idempotentHint=true, setting a safe read baseline. The description adds valuable behavioral context by specifying the summary is 'cached' (not freshly generated) and that the id must come from the search tools. This goes beyond the structured fields, though it does not mention edge cases like id-not-found behavior. No contradiction with annotations.

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?

The description is a single sentence with no filler. The core purpose (fetch by id) is front-loaded, and the optional summary behavior is appended concisely. Every phrase earns its place.

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 simple read-only lookup with two parameters and no output schema, the description covers the essential invocation details: which id to use and the optional summary. It could specify what the return payload contains, but 'Fetch one tender' reasonably implies tender details. Given the annotations and sibling context, 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 description coverage is 0%, so the description must compensate. It adds meaning to 'id' by explaining it comes from search tools, which is helpful. For summary_lang, the description only says 'optionally with a cached AI summary' and does not explicitly tie the parameter to selecting the summary language; the enum alone carries the allowed values. This is adequate but not fully compensating for the missing schema descriptions.

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 uses a specific verb ('Fetch'), names a precise resource ('one tender'), and identifies how to select it ('by its id as returned by the search tools'). It also distinguishes itself from sibling search and summarize tools by noting the optional cached AI summary. This clearly separates it from fulltext_search, search_tenders, and summarize_tender.

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 phrase 'as returned by the search tools' gives important usage context: this tool is for retrieving a specific tender once the id is known, not for discovery. It also implies a distinction from summarize_tender by describing the summary as 'cached' rather than generated. However, it does not explicitly state when NOT to use it or mention any alternatives beyond the implied search tools.

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