add_work

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

Annotations already establish a non-destructive, closed-world write, so the bar is lower; the description adds genuinely non-obvious behavior beyond that: records with matching identifiers and title are auto-reused, while conflicting ones are kept as separate records. This directly affects data integrity and is not derivable 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?

Two compact sentences with no filler; the required-field constraint and the supported identifiers are front-loaded, and the dedup caveat follows. Density is high without hurting readability.

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 two-parameter mutation with no output schema and an entirely undescribed nested metadata object, the description covers purpose, the required field, common fields, and dedup behavior. It omits what project_id means, what a successful call returns, and any permission expectations, so it is adequate but not fully self-contained.

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% and metadata is a free-form nested object with no property definitions, so the description's field list (title required, doi/pmid/arxiv, authors, year, journal, url) is the only documentation of metadata contents. However, project_id is left entirely unexplained in both schema and description, leaving a real gap.

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 names a concrete action and resource ('保存题录') and enumerates the metadata fields it accepts (title required; doi/pmid/arxiv, authors, year, journal, url), so an agent knows exactly what kind of record is created. It does not explicitly differentiate itself from sibling update_work, which prevents a 5.

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?

Usage is implied rather than stated: the dedup rule ('一致标识和标题才自动复用；冲突保留独立记录') tells the agent what happens on repeated submissions, which helps decide whether to call this versus update_work, but no alternative is named and no exclusions or prerequisites are given.

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