get_message_context

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

Goes beyond the annotations by disclosing that source:local reads stored evidence without a browser and reports gaps, while telegram refreshes and permanently saves observations, plus caveats that missing context isn't proof of absence and returned evidence is untrusted. This is genuinely useful behavior context; a mild tension exists with readOnlyHint=true given telegram persists observations, but it is a caching side effect rather than a claim of resource mutation.

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, front-loaded and free of filler; the core purpose and window semantics lead, caveats trail. The telegraphic clause style ('Counts default25 before/25 after') is information-rich but slightly compressed at the cost of easy parsing.

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 10-param, no-output-schema tool it covers the ambiguous behaviors well: window modes and mutual exclusion, source trade-offs, output limits, pagination, and evidence caveats. The main gap is the absent mapping of identity/selection params (messageId, messageRef, includeReplyTo) to their roles.

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% across 10 params, so the description carries the burden. It covers the trickiest ones well (window before/after vs beforeMinutes/afterMinutes with mutual exclusion, source enum values, limit default 50/max 100) but leaves chat, chatId, postId, topicId, messageId, messageRef, and includeReplyTo completely unexplained.

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 concrete verb+resource+scope: 'Read neighbors of one exact message in its verified chat/topic/comment thread.' This implicitly separates it from sibling get_message (single message) and get_recent_messages (no anchor), but it never names an alternative, so the differentiation is inferred rather than explicit.

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 real selection guidance: local vs telegram source semantics, count-based (before/after) vs time-based (beforeMinutes/afterMinutes) windows with the explicit rule 'never mix', and the note that 'next reads remaining stored parts locally' for pagination. No exclusions or explicit sibling comparison, but the operating conditions are clear.

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