jp_lit_record_ndl_browser_search

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

The description adds genuinely useful behavioral context beyond the annotations: it is a local-only write (readOnlyHint=false aligns), the MCP performs no browser operations, login, or external communication, and it does not receive cookies, credentials, images, or PDF bodies/paths. These negative constraints help the agent understand side-effect boundaries. It does not address idempotency (idempotentHint=false) implications, but no contradiction with annotations exists.

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 core purpose ('local write') is front-loaded, and the content is efficient with no filler. It packs the save action, the negative constraints, and the downstream workflow into three compact sentences. The single dense Japanese paragraph could be structurally split for readability, but it earns its sentences.

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 high-complexity tool (9 required params, deeply nested items/filters/snippets objects, multiple state enums), the description establishes the tool's role and downstream handling well but gives no guidance on assembling the complex input structure. The rich schema enums and output schema carry much of the load, and the negative constraints clarify boundaries, but an agent still lacks direction on how to populate items 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 only 11% (just session_id carries schema-level description), placing the burden on the tool description — but the description explains none of the 9 parameters. Its only parameter-related content is negative (states what it does not receive, e.g., cookies/images/PDFs). It gives no guidance on the complex items array, filters, or state enums, leaving the agent to infer semantics purely from enum names.

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?

Description states a specific action — verify full-text search candidates and their browse/in-document-search/print-PDF states observed on the official DigiCol screen, then save them to cache/session. The verb (save/record) and resource (observed candidates with their states) are clear, and its write nature distinguishes it from the many search/retrieval siblings. It lacks an explicit 'this is not X' pointer, so it doesn't fully reach the bar of the strongest examples.

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 context is implied: use when the agent has observed results on the official DigiCol screen that need verification and persistence. It names downstream consumers (jp_lit_refine_results, jp_lit_search_cache_index, jp_lit_annotate_session, jp_lit_export_view/export_session) which clarifies the workflow, but it never states when NOT to use this tool or how it compares to alternative write paths. No explicit exclusions.

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